Search

Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents an extensive empirical evaluation of Llama 3. We find that Llama 3 delivers comparable quality to leading language models such as GPT-4 on a plethora of tasks. We publicly release Llama 3, including pre-trained and post-trained versions of the 405B parameter language model and our Llama Guard 3 model for input and output safety. The paper also presents the results of experiments in which we integrate image, video, and speech capabilities into Llama 3 via a compositional approach. We observe this approach performs competitively with the state-of-the-art on image, video, and speech recognition tasks. The resulting models are not yet being broadly released as they are still under development.

Despite blockchain data being publicly available, practical challenges and high costs often hinder its effective use by researchers, thus limiting data-driven research and exploration in the blockchain space. This is especially true when it comes to Layer~2 (L2) ecosystems, and ZKsync, in particular. To address these issues, we have curated a dataset from 1 year of activity extracted from a ZKsync Era archive node and made it freely available to external parties. In this paper, we provide details on this dataset and how it was created, showcase a few example analyses that can be performed with it, and discuss some future research directions. We also publish and share the code used in our analysis on GitHub to promote reproducibility and to support further research., Comment: 12 pages, 12 figures

Blockchain platforms attempt to expand their user base by awarding tokens to users, a practice known as issuing airdrops. Empirical data and related work implies that previous airdrops fall short of their stated aim of attracting long-term users, partially due to adversarial farmers who game airdrop mechanisms and receive an outsize share of rewards. In this work, we argue that given the futility of fighting farmers, the airdrop business model should be reconsidered: farmers should be harnessed to generate activity that attracts real users, i.e., strengthens network effects. To understand the impact of farmers on airdrops, we analyze their performance in a market inhabited by two competing platforms and two tiers of users: real users and farmers. We show that counterintuitively, farmers sometimes represent a necessary evil-it can be revenue-optimal for airdrop issuers to give some tokens to farmers, even in the hypothetical case where platforms could costlessly detect and banish all farmers. Although we focus on airdrops, our results generally apply to activity-based incentive schemes., Comment: 27 pages, 3 figures

Blockchains like Bitcoin and Ethereum have revolutionized digital transactions, yet scalability issues persist. Layer 2 solutions, such as validity proof Rollups (ZK-Rollups), aim to address these challenges by processing transactions off-chain and validating them on the main chain. However, concerns remain about security and censorship resistance, particularly regarding centralized control in Layer 2 and inadequate mechanisms for enforcing these properties through Layer 1 contracts. This work presents a formal analysis using the Alloy specification language to examine and design key Layer 2 functionalities, including forced transaction queues, safe blacklisting, and upgradeability. Through this analysis, we identify potential vulnerabilities in current mechanisms and propose enhanced models to strengthen security and censorship resistance, setting new standards for the security of rollups.

Spoken Language Understanding (SLU) is a critical component of voice assistants; it consists of converting speech to semantic parses for task execution. Previous works have explored end-to-end models to improve the quality and robustness of SLU models with Deliberation, however these models have remained autoregressive, resulting in higher latencies. In this work we introduce PRoDeliberation, a novel method leveraging a Connectionist Temporal Classification-based decoding strategy as well as a denoising objective to train robust non-autoregressive deliberation models. We show that PRoDeliberation achieves the latency reduction of parallel decoding (2-10x improvement over autoregressive models) while retaining the ability to correct Automatic Speech Recognition (ASR) mistranscriptions of autoregressive deliberation systems. We further show that the design of the denoising training allows PRoDeliberation to overcome the limitations of small ASR devices, and we provide analysis on the necessity of each component of the system.

This paper explores the dynamics of Decentralized Finance (DeFi) within the Layer-2 ecosystem, focusing on Automated Market Makers (AMM) and arbitrage on Ethereum rollups. We observe significant shifts in trading activity from Ethereum to rollups, with swaps on rollups happening 2-3 times more often, though, with lower trade volume. By examining the price differences between AMMs and centralized exchanges, we discover over 0.5 million unexploited arbitrage opportunities on rollups. Remarkably, we observe that these opportunities last, on average, 10 to 20 blocks, requiring adjustments to the LVR metrics to avoid double-counting arbitrage. Our results show that arbitrage in Arbitrum, Base, and Optimism pools ranges from 0.03% to 0.05% of trading volume, while in zkSync Era it oscillates around 0.25%, with the LVR metric overestimating arbitrage by a factor of five. Rollups offer not only lower gas fees, but also provide faster block production, leading to significant differences compared to the trading and arbitrage dynamics of Ethereum.

Despite the level of attention given to rollups there is limited empirical research about their performance. To address this gap, we conduct a comprehensive data-driven analysis of the late 2023 transaction boom that is attributed to inscriptions: a novel approach to record data onto a blockchain with no outside server needed. Inscriptions were first introduced on the Bitcoin blockchain to allow for the representation of NFTs or ERC-20-like tokens without smart contracts, but were later spread to other blockchains. This work examines the applications of inscription transactions in Ethereum and its major EVM-compatible rollups and their impact on blockchain scalability during periods of sudden transaction surges. We found that on certain days, inscription-related transactions comprised over 89% on Arbitrum, over 88% on zkSync Era, and over 53% on Ethereum. Furthermore, 99% of these transactions were related to the minting of meme coins, followed by limited trading activity. Unlike L1 blockchains, during periods of transaction surges, zkSync and Arbitrum experienced lower median gas fees, attributable to the compression of L2 transactions for a single L1 batch. Additionally, zkSync Era, a ZK rollup, demonstrated a stronger reduction in fees than optimistic rollups considered in our study: Arbitrum, Base, and Optimism., Comment: This research article is a work of scholarship and reflects the authors' own views and opinions. It does not necessarily reflect the views or opinions of any other person or organization, including the authors' employer. Readers should not rely on this article for making strategic or commercial decisions, and the authors are not responsible for any losses that may result from such use. arXiv admin note: substantial text overlap with arXiv:2404.11189

Plonkish is a popular circuit format for developing zero-knowledge proof systems that powers a number of major projects in the blockchain space, responsible for holding billions of dollars and processing millions of transactions per day. These projects, including zero-knowledge rollups, rely on highly hand-optimized circuits whose correctness comes at the cost of time-consuming testing and auditing. In this paper, we present Clap, the first Rust eDSL with a proof system agnostic circuit format, facilitating extensibility, automatic optimizations, and formal assurances for the resultant constraint system. Clap casts the problem of producing Plonkish constraint systems and their witness generators as a semantic-preserving compilation problem. Soundness and completeness of the transformation guarantees the absence of subtle bugs caused by under- or over-constraining. Our experimental evaluation shows that its automatic optimizations achieve better performance compared to manual circuit optimization. The optimizer can also be used to automatically derive custom gates from circuit descriptions.

Late 2023 witnessed significant user activity on EVM chains, resulting in a surge in transaction activity and putting many rollups into the first live test. While some rollups performed well, some others experienced downtime during this period, affecting transaction finality time and gas fees. To address the lack of empirical research on rollups, we perform the first study during a heightened activity during the late 2023 transaction boom, as attributed to inscriptions - a novel technique that enables NFT and ERC-20 token creation on Bitcoin and other blockchains. We observe that minting inscription-based meme tokens on zkSync Era allows for trading at a fraction of the costs, compared to the Bitcoin or Ethereum networks. We also found that the increased transaction activity, over 99% attributed to the minting of new inscription tokens, positively affected other users of zkSync Era, resulting in lowered gas fees. Unlike L1 blockchains, ZK rollups may experience lower gas fees with increased transaction volume. Lastly, the introduction of blobs - a form of temporary data storage - decreased the gas costs of Ethereum rollups, but also raised a number of questions about the security of inscription-based tokens., Comment: Work in progress, exploring zkSync Era. More EVM chains will be added in the final version

In ZK-Rollups, provers spend significant computational resources to generate validity proofs. Their costs should be compensated properly, so a sustainable prover market can form over time. Existing transaction fee mechanisms (TFMs) such as EIP-1559, however, do not work in this setting, as EIP-1559 only generates negligible revenue because of burning, while provers often create or purchase specialized hardware in hopes of creating long-term revenue from proving, somewhat reminiscent of proof-of-work miners in the case of chains like Bitcoin. In this paper, we explore the design of transaction fee mechanisms for prover markets. The desiderata for such mechanisms include efficiency (social welfare is maximized), incentive compatibility (it is rational to bid honestly), collusion resistance (no profitable collusion among provers exists), and off-chain agreement proofness (no profitable collusion between users and provers exists). To demonstrate the difficulties of our new setting, we put forward several simple strawman mechanisms, and show they suffer from notable deficiencies.

In the rapidly progressing field of generative models, the development of efficient and high-fidelity text-to-image diffusion systems represents a significant frontier. This study introduces YaART, a novel production-grade text-to-image cascaded diffusion model aligned to human preferences using Reinforcement Learning from Human Feedback (RLHF). During the development of YaART, we especially focus on the choices of the model and training dataset sizes, the aspects that were not systematically investigated for text-to-image cascaded diffusion models before. In particular, we comprehensively analyze how these choices affect both the efficiency of the training process and the quality of the generated images, which are highly important in practice. Furthermore, we demonstrate that models trained on smaller datasets of higher-quality images can successfully compete with those trained on larger datasets, establishing a more efficient scenario of diffusion models training. From the quality perspective, YaART is consistently preferred by users over many existing state-of-the-art models., Comment: Prompts and additional information are available on the project page, see https://ya.ru/ai/art/paper-yaart-v1

Arbitrage can arise from the simultaneous purchase and sale of the same asset in different markets in order to profit from a difference in its price. This work systematically reviews arbitrage opportunities between Automated Market Makers (AMMs) on Ethereum ZK rollups, and Centralised Exchanges (CEXs). First, we propose a theoretical framework to measure such arbitrage opportunities and derive a formula for the related Maximal Arbitrage Value (MAV) that accounts for both price divergences and liquidity available in the trading venues. Then, we empirically measure the historical MAV available between SyncSwap, an AMM on zkSync Era, and Binance, and investigate how quickly misalignments in price are corrected against explicit and implicit market costs. Overall, the cumulative MAV from July to September 2023 on the USDC-ETH SyncSwap pool amounts to $104.96k (0.24% of trading volume)., Comment: In proceedings of Marble 2024

Every $n$-tuple in $\mathbb{F}^{n}$ has a first non-zero entry and a last non-zero entry. What do the positions of such entries in the elements of a subspace W of $\mathbb{F}^{n}$ reveal about W? It turns out, a great deal! This insight offers a beeline to the fundamental results on general bases and dimension (including dimensions of complements, rank of a transpose, Rank-Nullity Theorem, Full Rank Factorization, and existence/uniqueness of RREF), bypassing some of the traditional stumbling blocks and time sinks.

Zero-knowledge proofs (ZKPs) have evolved from being a theoretical concept providing privacy and verifiability to having practical, real-world implementations, with SNARKs (Succinct Non-Interactive Argument of Knowledge) emerging as one of the most significant innovations. Prior work has mainly focused on designing more efficient SNARK systems and providing security proofs for them. Many think of SNARKs as "just math," implying that what is proven to be correct and secure is correct in practice. In contrast, this paper focuses on assessing end-to-end security properties of real-life SNARK implementations. We start by building foundations with a system model and by establishing threat models and defining adversarial roles for systems that use SNARKs. Our study encompasses an extensive analysis of 141 actual vulnerabilities in SNARK implementations, providing a detailed taxonomy to aid developers and security researchers in understanding the security threats in systems employing SNARKs. Finally, we evaluate existing defense mechanisms and offer recommendations for enhancing the security of SNARK-based systems, paving the way for more robust and reliable implementations in the future.

Attribution scores can be applied in data management to quantify the contribution of individual items to conclusions from the data, as part of the explanation of what led to these conclusions. In Artificial Intelligence, Machine Learning, and Data Management, some of the common scores are deployments of the Shapley value, a formula for profit sharing in cooperative game theory. Since its invention in the 1950s, the Shapley value has been used for contribution measurement in many fields, from economics to law, with its latest researched applications in modern machine learning. Recent studies investigated the application of the Shapley value to database management. This article gives an overview of recent results on the computational complexity of the Shapley value for measuring the contribution of tuples to query answers and to the extent of inconsistency with respect to integrity constraints. More specifically, the article highlights lower and upper bounds on the complexity of calculating the Shapley value, either exactly or approximately, as well as solutions for realizing the calculation in practice., Comment: 12 pages, including references. This is the authors version of the corresponding SIGMOD Record article

Operational consistent query answering (CQA) is a recent framework for CQA based on revised definitions of repairs, which are built by applying a sequence of operations (e.g., fact deletions) starting from an inconsistent database until we reach a database that is consistent w.r.t. the given set of constraints. It has been recently shown that there are efficient approximations for computing the percentage of repairs, as well as of sequences of operations leading to repairs, that entail a given query when we focus on primary keys, conjunctive queries, and assuming the query is fixed (i.e., in data complexity). However, it has been left open whether such approximations exist when the query is part of the input (i.e., in combined complexity). We show that this is the case when we focus on self-join-free conjunctive queries of bounded generelized hypertreewidth. We also show that it is unlikely that efficient approximation schemes exist once we give up one of the adopted syntactic restrictions, i.e., self-join-freeness or bounding the generelized hypertreewidth. Towards the desired approximation schemes, we introduce a novel counting complexity class, called SpanTL, show that each problem in SpanTL admits an efficient approximation scheme by using a recent approximability result in the context of tree automata, and then place the problems of interest in SpanTL.

Airdrops are used by blockchain applications and protocols to attract an initial user base, and to grow the user base over time. In the case of many airdrops, tokens are distributed to select users as a "reward" for interacting with the underlying protocol, with a long-term goal of creating a loyal community that will generate genuine economic activity well after the airdrop. Although airdrops are widely used by the blockchain industry, a proper understanding of the factors contributing to an airdrop's success is generally lacking. In this work, we outline the design space for airdrops, and specify a reasonable list of outcomes that an airdrop should ideally result in. We then analyze on-chain data from several larger-scale airdrops to empirically evaluate the success of previous airdrops, with respect to our desiderata. In our analysis, we demonstrate that airdrop farmers frequently dispose of the lion's share of airdrops proceeds via exchanges. Our analysis is followed by an overview of common pitfalls that common airdrop designs lend themselves to, which are then used to suggest concrete guidelines for better airdrops., Comment: This research article is a work of scholarship and reflects the authors' own views and opinions. It does not necessarily reflect the views or opinions of any other person or organization, including the authors' employer. Readers should not rely on this article for making strategic or commercial decisions, and the authors are not responsible for any losses that may result from such use

We study the problem of how to coordinate the actions of independent agents in a distributed system where message arrival times are unbounded, but are determined by an exponential probability distribution. Asynchronous protocols executed in such a model are guaranteed to succeed with probability 1. We demonstrate a case in which the best asynchronous protocol can be improved on significantly. Specifically, we focus on the task of performing actions by different agents in a linear temporal order -- a problem known in the literature as Ordered Response. In asynchronous systems, ensuring such an ordering requires the construction of a message chain that passes through each acting agent, in order. Solving Ordered Response in this way in our model will terminate in time that grows linearly in the number of participating agents $n$, in expectation. We show that relaxing the specification slightly allows for a significant saving in time. Namely, if Ordered Response should be guaranteed with high probability (arbitrarily close to 1), it is possible to significantly shorten the expected execution time of the protocol. We present two protocols that adhere to the relaxed specification. One of our protocols executes exponentially faster than a message chain, when the number of participating agents $n$ is large, while the other is roughly quadratically faster. For small values of $n$, it is also possible to achieve similar results by using a hybrid protocol., Comment: The paper is 20 pages long and contains 3 figures. It is to be published in the 2023 Conference on Principles of Distributed Systems (OPODIS)

Rollups have emerged as a promising solution to enhance blockchain scalability, offering increased throughput, reduced latency, and lower transaction fees. However, they currently rely on a centralized sequencer to determine transaction ordering, compromising the decentralization principle of blockchain systems. Recognizing this, there is a clear need for decentralized sequencers in rollups. However, designing such a system is intricate. This paper presents a comprehensive exploration of decentralized sequencers in rollups, formulating their ideal properties, dissecting their core components, and synthesizing community insights. Our findings emphasize the imperative for an adept sequencer design, harmonizing with the overarching goals of the blockchain ecosystem, and setting a trajectory for subsequent research endeavors.

While cryptocurrencies have been rapidly gaining adoption, secure wallet interactions are still elusive for many users, which frequently leads to loss of funds. Here we propose an approach to securing interactions with cryptocurrency wallets for end-users. The approach called FailSafe consists of several defence-in-depth measures that can be applied near-term as well as a tool called qMig for aiding eventual quantum migration.

The growth of the decentralized finance (DeFi) ecosystem built on blockchain technology and smart contracts has led to an increased demand for secure and reliable smart contract development. However, attacks targeting smart contracts are increasing, causing an estimated \$6.45 billion in financial losses. Researchers have proposed various automated security tools to detect vulnerabilities, but their real-world impact remains uncertain. In this paper, we aim to shed light on the effectiveness of automated security tools in identifying vulnerabilities that can lead to high-profile attacks, and their overall usage within the industry. Our comprehensive study encompasses an evaluation of five SoTA automated security tools, an analysis of 127 high-impact real-world attacks resulting in \$2.3 billion in losses, and a survey of 49 developers and auditors working in leading DeFi protocols. Our findings reveal a stark reality: the tools could have prevented a mere 8% of the attacks in our dataset, amounting to \$149 million out of the \$2.3 billion in losses. Notably, all preventable attacks were related to reentrancy vulnerabilities. Furthermore, practitioners distinguish logic-related bugs and protocol layer vulnerabilities as significant threats that are not adequately addressed by existing security tools. Our results emphasize the need to develop specialized tools catering to the distinct demands and expectations of developers and auditors. Further, our study highlights the necessity for continuous advancements in security tools to effectively tackle the ever-evolving challenges confronting the DeFi ecosystem.

The use of blockchains for automated and adversarial trading has become commonplace. However, due to the transparent nature of blockchains, an adversary is able to observe any pending, not-yet-mined transactions, along with their execution logic. This transparency further enables a new type of adversary, which copies and front-runs profitable pending transactions in real-time, yielding significant financial gains. Shedding light on such "copy-paste" malpractice, this paper introduces the Blockchain Imitation Game and proposes a generalized imitation attack methodology called Ape. Leveraging dynamic program analysis techniques, Ape supports the automatic synthesis of adversarial smart contracts. Over a timeframe of one year (1st of August, 2021 to 31st of July, 2022), Ape could have yielded 148.96M USD in profit on Ethereum, and 42.70M USD on BNB Smart Chain (BSC). Not only as a malicious attack, we further show the potential of transaction and contract imitation as a defensive strategy. Within one year, we find that Ape could have successfully imitated 13 and 22 known Decentralized Finance (DeFi) attacks on Ethereum and BSC, respectively. Our findings suggest that blockchain validators can imitate attacks in real-time to prevent intrusions in DeFi.

Autoregressive (AR) encoder-decoder neural networks have proved successful in many NLP problems, including Semantic Parsing -- a task that translates natural language to machine-readable parse trees. However, the sequential prediction process of AR models can be slow. To accelerate AR for semantic parsing, we introduce a new technique called TreePiece that tokenizes a parse tree into subtrees and generates one subtree per decoding step. On TopV2 benchmark, TreePiece shows 4.6 times faster decoding speed than standard AR, and comparable speed but significantly higher accuracy compared to Non-Autoregressive (NAR)., Comment: 4 pages main body + 4 pages appendices

Explaining why a database query result is obtained is an essential task towards the goal of Explainable AI, especially nowadays where expressive database query languages such as Datalog play a critical role in the development of ontology-based applications. A standard way of explaining a query result is the so-called why-provenance, which essentially provides information about the witnesses to a query result in the form of subsets of the input database that are sufficient to derive that result. To our surprise, despite the fact that the notion of why-provenance for Datalog queries has been around for decades and intensively studied, its computational complexity remains unexplored. The goal of this work is to fill this apparent gap in the why-provenance literature. Towards this end, we pinpoint the data complexity of why-provenance for Datalog queries and key subclasses thereof. The takeaway of our work is that why-provenance for recursive queries, even if the recursion is limited to be linear, is an intractable problem, whereas for non-recursive queries is highly tractable. Having said that, we experimentally confirm, by exploiting SAT solvers, that making why-provenance for (recursive) Datalog queries work in practice is not an unrealistic goal.

In recent years, decentralized finance (DeFi) has experienced remarkable growth, with various protocols such as lending protocols and automated market makers (AMMs) emerging. Traditionally, these protocols employ off-chain governance, where token holders vote to modify parameters. However, manual parameter adjustment, often conducted by the protocol's core team, is vulnerable to collusion, compromising the integrity and security of the system. Furthermore, purely deterministic, algorithm-based approaches may expose the protocol to novel exploits and attacks. In this paper, we present "Auto.gov", a learning-based on-chain governance framework for DeFi that enhances security and reduces susceptibility to attacks. Our model leverages a deep Q- network (DQN) reinforcement learning approach to propose semi-automated, intuitive governance proposals with quantitative justifications. This methodology enables the system to efficiently adapt to and mitigate the negative impact of malicious behaviors, such as price oracle attacks, more effectively than benchmark models. Our evaluation demonstrates that Auto.gov offers a more reactive, objective, efficient, and resilient solution compared to existing manual processes, thereby significantly bolstering the security and, ultimately, enhancing the profitability of DeFi protocols.

In Federated Learning (FL), accessing private client data incurs communication and privacy costs. As a result, FL deployments commonly prefinetune pretrained foundation models on a (large, possibly public) dataset that is held by the central server; they then FL-finetune the model on a private, federated dataset held by clients. Evaluating prefinetuning dataset quality reliably and privately is therefore of high importance. To this end, we propose FreD (Federated Private Fr\'echet Distance) -- a privately computed distance between a prefinetuning dataset and federated datasets. Intuitively, it privately computes and compares a Fr\'echet distance between embeddings generated by a large language model on both the central (public) dataset and the federated private client data. To make this computation privacy-preserving, we use distributed, differentially-private mean and covariance estimators. We show empirically that FreD accurately predicts the best prefinetuning dataset at minimal privacy cost. Altogether, using FreD we demonstrate a proof-of-concept for a new approach in private FL training: (1) customize a prefinetuning dataset to better match user data (2) prefinetune (3) perform FL-finetuning.

We demonstrate that the radial magnetic-field component at the outer boundary of the sunspot penumbra is about 550 Mx cm$^{-2}$ independent of the sunspot area and the maximum magnetic field in the umbra. The mean magnetic-field intensity in sunspots grows slightly as the sunspot area increases up to 500 -- 1000 millionth of visual hemisphere (m.v.h.) and may reach about 900 -- 2000 Mx cm$^{-2}$. The total magnetic flux weakly depends on the maximum field strength in a sunspot and is determined by the spottedness, i.e. the sunspot number and the total sunspot area; however, the relation between the total flux and the sunspot area is substantially nonlinear. We suggest an explicit parametrization for this relation. The contribution of the magnetic flux associated with sunspots to the total magnetic flux is small, not achieving more than 20% even at the maximum of the solar activity., Comment: 13 pages, 8 figures. Accepted for publication in Solar Physics

We demonstrate that for weak flares the dependence on spottedness can be rather weak. The fact is that such flares can occur both in small and large active regions. At the same time, powerful large flares of classes M and X occur much more often in large active regions. In energy estimates, the mean magnetic field in starspots can also be assumed equal to the mean field in the sunspot umbra. So the effective mean magnetic field is 900 Mx/cm$^2$ in sunspots and 2000 Mx/cm$^2$ in starspots. Moreover, the height of the energy storage cannot be strictly proportional to A$^{1/2}$. For stars, the fitting factor is an order of magnitude smaller. The analysis of the occurrence rate of powerful solar X-ray flares of class M and X and superflares on stars shows that, with allowance for the difference in the spottedness and compactness of active regions, both sets can be described by a single model. Thus, the problem of superflares on stars and their absence on the Sun is reduced to the problem of difference in the effectiveness of the dynamo mechanisms., Comment: 15 pages, 4 figures, 1 table. Accepted to ApJ

Operational consistent query answering (CQA) is a recent framework for CQA, based on revised definitions of repairs and consistent answers, which opens up the possibility of efficient approximations with explicit error guarantees. The main idea is to iteratively apply operations (e.g., fact deletions), starting from an inconsistent database, until we reach a database that is consistent w.r.t. the given set of constraints. This gives us the flexibility of choosing the probability with which we apply an operation, which in turn allows us to calculate the probability of an operational repair, and thus, the probability with which a consistent answer is entailed. A natural way of assigning probabilities to operations is by targeting the uniform probability distribution over a reasonable space such as the set of operational repairs, the set of sequences of operations that lead to an operational repair, and the set of available operations at a certain step of the repairing process. This leads to what we generally call uniform operational CQA. The goal of this work is to perform a data complexity analysis of both exact and approximate uniform operational CQA, focusing on functional dependencies (and subclasses thereof), and conjunctive queries. The main outcome of our analysis (among other positive and negative results), is that uniform operational CQA pushes the efficiency boundaries further by ensuring the existence of efficient approximation schemes in scenarios that go beyond the simple case of primary keys, which seems to be the limit of the classical approach to CQA.

We propose a novel deliberation-based approach to end-to-end (E2E) spoken language understanding (SLU), where a streaming automatic speech recognition (ASR) model produces the first-pass hypothesis and a second-pass natural language understanding (NLU) component generates the semantic parse by conditioning on both ASR's text and audio embeddings. By formulating E2E SLU as a generalized decoder, our system is able to support complex compositional semantic structures. Furthermore, the sharing of parameters between ASR and NLU makes the system especially suitable for resource-constrained (on-device) environments; our proposed approach consistently outperforms strong pipeline NLU baselines by 0.60% to 0.65% on the spoken version of the TOPv2 dataset (STOP). We demonstrate that the fusion of text and audio features, coupled with the system's ability to rewrite the first-pass hypothesis, makes our approach more robust to ASR errors. Finally, we show that our approach can significantly reduce the degradation when moving from natural speech to synthetic speech training, but more work is required to make text-to-speech (TTS) a viable solution for scaling up E2E SLU., Comment: Accepted for publication at INTERSPEECH 2022

A core problem in the development and maintenance of crowd-sourced filter lists is that their maintainers cannot confidently predict whether (and where) a new filter list rule will break websites. This is a result of enormity of the Web, which prevents filter list authors from broadly understanding the impact of a new blocking rule before they ship it to millions of users. The inability of filter list authors to evaluate the Web compatibility impact of a new rule before shipping it severely reduces the benefits of filter-list-based content blocking: filter lists are both overly-conservative (i.e. rules are tailored narrowly to reduce the risk of breaking things) and error-prone (i.e. blocking tools still break large numbers of sites). To scale to the size and scope of the Web, filter list authors need an automated system to detect when a new filter rule breaks websites, before that breakage has a chance to make it to end users. In this work, we design and implement the first automated system for predicting when a filter list rule breaks a website. We build a classifier, trained on a dataset generated by a combination of compatibility data from the EasyList project and novel browser instrumentation, and find it is accurate to practical levels (AUC 0.88). Our open source system requires no human interaction when assessing the compatibility risk of a proposed privacy intervention. We also present the 40 page behaviors that most predict breakage in observed websites.

Task-oriented semantic parsing models have achieved strong results in recent years, but unfortunately do not strike an appealing balance between model size, runtime latency, and cross-domain generalizability. We tackle this problem by introducing scenario-based semantic parsing: a variant of the original task which first requires disambiguating an utterance's "scenario" (an intent-slot template with variable leaf spans) before generating its frame, complete with ontology and utterance tokens. This formulation enables us to isolate coarse-grained and fine-grained aspects of the task, each of which we solve with off-the-shelf neural modules, also optimizing for the axes outlined above. Concretely, we create a Retrieve-and-Fill (RAF) architecture comprised of (1) a retrieval module which ranks the best scenario given an utterance and (2) a filling module which imputes spans into the scenario to create the frame. Our model is modular, differentiable, interpretable, and allows us to garner extra supervision from scenarios. RAF achieves strong results in high-resource, low-resource, and multilingual settings, outperforming recent approaches by wide margins despite, using base pre-trained encoders, small sequence lengths, and parallel decoding.

Advances in cloud computing have simplified the way that both software development and testing are performed. This is not true for battery testing for which state of the art test-beds simply consist of one phone attached to a power meter. These test-beds have limited resources, access, and are overall hard to maintain; for these reasons, they often sit idle with no experiment to run. In this paper, we propose to share existing battery testbeds and transform them into vantage points of BatteryLab, a power monitoring platform offering heterogeneous devices and testing conditions. We have achieved this vision with a combination of hardware and software which allow to augment existing battery test-beds with remote capabilities. BatteryLab currently counts three vantage points, one in Europe and two in the US, hosting three Android devices and one iPhone 7. We benchmark BatteryLab with respect to the accuracy of its battery readings, system performance, and platform heterogeneity. Next, we demonstrate how measurements can be run atop of BatteryLab by developing the "Web Power Monitor" (WPM), a tool which can measure website power consumption at scale. We released WPM and used it to report on the energy consumption of Alexa's top 1,000 websites across 3 locations and 4 devices (both Android and iOS)., Comment: 25 pages, 11 figures, Passive and Active Measurement Conference 2022 (PAM '22). arXiv admin note: text overlap with arXiv:1910.08951

Zero-knowledge proof (ZKP) mixers are one of the most widely-used blockchain privacy solutions, operating on top of smart contract-enabled blockchains. We find that ZKP mixers are tightly intertwined with the growing number of Decentralized Finance (DeFi) attacks and Blockchain Extractable Value (BEV) extractions. Through coin flow tracing, we discover that 205 blockchain attackers and 2,595 BEV extractors leverage mixers as their source of funds, while depositing a total attack revenue of 412.87M USD. Moreover, the US OFAC sanctions against the largest ZKP mixer, Tornado.Cash, have reduced the mixer's daily deposits by more than 80%. Further, ZKP mixers advertise their level of privacy through a so-called anonymity set size, which similarly to k-anonymity allows a user to hide among a set of k other users. Through empirical measurements, we, however, find that these anonymity set claims are mostly inaccurate. For the most popular mixers on Ethereum (ETH) and Binance Smart Chain (BSC), we show how to reduce the anonymity set size on average by 27.34% and 46.02% respectively. Our empirical evidence is also the first to suggest a differing privacy-predilection of users on ETH and BSC. State-of-the-art ZKP mixers are moreover interwoven with the DeFi ecosystem by offering anonymity mining (AM) incentives, i.e., users receive monetary rewards for mixing coins. However, contrary to the claims of related work, we find that AM does not necessarily improve the quality of a mixer's anonymity set. Our findings indicate that AM attracts privacy-ignorant users, who then do not contribute to improving the privacy of other mixer users.