Search

Protecting sensitive information in diagnostic data such as logs, is a critical concern in the industrial software diagnosis and debugging process. While there are many tools developed to automatically redact the logs for identifying and removing sensitive information, they have severe limitations which can cause either over redaction and loss of critical diagnostic information (false positives), or disclosure of sensitive information (false negatives), or both. To address the problem, in this paper, we argue for a source code analysis approach for log redaction. To identify a log message containing sensitive information, our method locates the corresponding log statement in the source code with logger code augmentation, and checks if the log statement outputs data from sensitive sources by using the data flow graph built from the source code. Appropriate redaction rules are further applied depending on the sensitiveness of the data sources to preserve the privacy information in the logs. We conducted experimental evaluation and comparison with other popular baselines. The results demonstrate that our approach can significantly improve the detection precision of the sensitive information and reduce both false positives and negatives.

Effective fraud detection and analysis of government-issued identity documents, such as passports, driver's licenses, and identity cards, are essential in thwarting identity theft and bolstering security on online platforms. The training of accurate fraud detection and analysis tools depends on the availability of extensive identity document datasets. However, current publicly available benchmark datasets for identity document analysis, including MIDV-500, MIDV-2020, and FMIDV, fall short in several respects: they offer a limited number of samples, cover insufficient varieties of fraud patterns, and seldom include alterations in critical personal identifying fields like portrait images, limiting their utility in training models capable of detecting realistic frauds while preserving privacy. In response to these shortcomings, our research introduces a new benchmark dataset, IDNet, designed to advance privacy-preserving fraud detection efforts. The IDNet dataset comprises 837,060 images of synthetically generated identity documents, totaling approximately 490 gigabytes, categorized into 20 types from $10$ U.S. states and 10 European countries. We evaluate the utility and present use cases of the dataset, illustrating how it can aid in training privacy-preserving fraud detection methods, facilitating the generation of camera and video capturing of identity documents, and testing schema unification and other identity document management functionalities., Comment: 40 pages

Lane-changing is a critical maneuver of vehicle driving, and a comprehensive understanding of its impact on traffic is essential for effective traffic management and optimization. Unfortunately, existing studies fail to adequately distinguish the impact of lane changes from those resulting from natural traffic dynamics. Additionally, there is a lack of precise methods for measuring the spatial extent and duration of the impact of a single discretionary lane change, as well as a definitive metric to quantify the overall spatiotemporal impact. To address these gaps, this study introduces a quantitative indicator called the Corrected Travel Distance Bias (CTDB), which accounts for variable speeds due to inherent traffic dynamics, providing a more accurate assessment of lane-changing impacts. A comprehensive methodology is developed to compare vehicle trajectory data before and after lane-changing events, measuring both the magnitude and spatiotemporal extent of the lane-changing impact. The results, based on the Zen traffic data from Japan, indicate that the impact of a lane change in the target lane lasts an average of 23.8 seconds, affecting approximately 5.6 vehicles, with a CTDB value of -10.8 meters. In contrast, in the original lane, the impact lasts 25 seconds, affects 5.3 vehicles, and yields a CTDB value of 4.7 meters.

The human-like automatic deductive reasoning has always been one of the most challenging open problems in the interdiscipline of mathematics and artificial intelligence. This paper is the third in a series of our works. We built a neural-symbolic system, called FGeoDRL, to automatically perform human-like geometric deductive reasoning. The neural part is an AI agent based on reinforcement learning, capable of autonomously learning problem-solving methods from the feedback of a formalized environment, without the need for human supervision. It leverages a pre-trained natural language model to establish a policy network for theorem selection and employ Monte Carlo Tree Search for heuristic exploration. The symbolic part is a reinforcement learning environment based on geometry formalization theory and FormalGeo, which models GPS as a Markov Decision Process. In this formal symbolic system, the known conditions and objectives of the problem form the state space, while the set of theorems forms the action space. Leveraging FGeoDRL, we have achieved readable and verifiable automated solutions to geometric problems. Experiments conducted on the formalgeo7k dataset have achieved a problem-solving success rate of 86.40%. The project is available at https://github.com/PersonNoName/FGeoDRL., Comment: 15 pages

The application of contemporary artificial intelligence techniques to address geometric problems and automated deductive proof has always been a grand challenge to the interdiscipline field of mathematics and artificial Intelligence. This is the fourth article in a series of our works, in our previous work, we established of a geometric formalized system known as FormalGeo. Moreover we annotated approximately 7000 geometric problems, forming the FormalGeo7k dataset. Despite the FGPS (Formal Geometry Problem Solver) can achieve interpretable algebraic equation solving and human-like deductive reasoning, it often experiences timeouts due to the complexity of the search strategy. In this paper, we introduced FGeo-TP (Theorem Predictor), which utilizes the language model to predict theorem sequences for solving geometry problems. We compared the effectiveness of various Transformer architectures, such as BART or T5, in theorem prediction, implementing pruning in the search process of FGPS, thereby improving its performance in solving geometry problems. Our results demonstrate a significant increase in the problem-solving rate of the language model-enhanced FGeo-TP on the FormalGeo7k dataset, rising from 39.7% to 80.86%. Furthermore, FGeo-TP exhibits notable reductions in solving time and search steps across problems of varying difficulty levels., Comment: 16 pages

It is challenging to select the right privacy-preserving mechanism for federated query processing over multiple private data silos. There exist numerous privacy-preserving mechanisms, such as secure multi-party computing (SMC), approximate query processing with differential privacy (DP), combined SMC and DP, DP-based data obfuscation, and federated learning. These mechanisms make different trade-offs among accuracy, privacy, execution efficiency, and storage efficiency. In this work, we first introduce a new privacy-preserving technique that uses a deep learning model trained using the Differentially-Private Stochastic Gradient Descent (DP-SGD) algorithm to replace portions of actual data to answer a query. We then demonstrate a novel declarative privacy-preserving workflow that allows users to specify "what private information to protect" rather than "how to protect". Under the hood, the system relies on a cost model to automatically choose privacy-preserving mechanisms as well as hyper-parameters. At the same time, the proposed workflow also allows human experts to review and tune the selected privacy-preserving mechanism for audit/compliance, and optimization purposes.

Chiral excitation flows have drawn a lot of attention for their unique unidirectionality. Such flows have been studied in three-node networks with synthetic gauge fields (SGFs), while they are barely realized as the number of nodes increases. In this work, we propose a scheme to achieve chiral flows in $n$-node networks, where an auxiliary node is introduced to govern the system. This auxiliary node is coupled to all the network nodes, forming sub-triangle structures with interference paths in these networks. We find the implicit chiral symmetry behind the perfect chiral flow and propose the universal criteria that incorporate previous models, facilitating the implementation of chiral transmission in various networks. By investigating the symmetries within these models, we present different features of the chiral flow in bosonic and spin networks. Furthermore, we extend the four-node model into a ladder network, which is promising for remote state transfer in practical systems with less complexity. Our scheme can be realized in state-of-the-art experimental systems, such as superconducting circuits and magnetic photonic lattices, thereby opening up new possibilities for future quantum networks., Comment: 17 pages, 11 figures

Urban Building Energy Modeling (UBEM) is a critical tool to provide quantitative analysis on building decarbonization, sustainability, building-to-grid integration, and renewable energy applications on city, regional, and national scales. Researchers usually use open data as inputs to build and calibrate UBEM. However, open data are from thousands of sources covering various perspectives of weather, building characteristics, etc. Besides, a lack of semantic features of open data further increases the engineering effort to process information to be directly used for UBEM as inputs. In this paper, we first reviewed open data types used for UBEM and developed a taxonomy to categorize open data. Based on that, we further developed a semantic data schema for each open data category to maintain data consistency and improve model automation for UBEM. In a case study, we use three popular open data to show how they can be automatically processed based on the proposed schematic data structure using large language models. The accurate results generated by large language models indicate the machine-readability and human-interpretability of the developed semantic data schema.

This is the first paper in a series of work we have accomplished over the past three years. In this paper, we have constructed a consistent formal plane geometry system. This will serve as a crucial bridge between IMO-level plane geometry challenges and readable AI automated reasoning. Within this formal framework, we have been able to seamlessly integrate modern AI models with our formal system. AI is now capable of providing deductive reasoning solutions to IMO-level plane geometry problems, just like handling other natural languages, and these proofs are readable, traceable, and verifiable. We propose the geometry formalization theory (GFT) to guide the development of the geometry formal system. Based on the GFT, we have established the FormalGeo, which consists of 88 geometric predicates and 196 theorems. It can represent, validate, and solve IMO-level geometry problems. we also have crafted the FGPS (formal geometry problem solver) in Python. It serves as both an interactive assistant for verifying problem-solving processes and an automated problem solver. We've annotated the formalgeo7k and formalgeo-imo datasets. The former contains 6,981 (expand to 133,818 through data augmentation) geometry problems, while the latter includes 18 (expand to 2,627 and continuously increasing) IMO-level challenging geometry problems. All annotated problems include detailed formal language descriptions and solutions. Implementation of the formal system and experiments validate the correctness and utility of the GFT. The backward depth-first search method only yields a 2.42% problem-solving failure rate, and we can incorporate deep learning techniques to achieve lower one. The source code of FGPS and datasets are available at https://github.com/BitSecret/FGPS., Comment: 44 pages

Serving deep learning (DL) models on relational data has become a critical requirement across diverse commercial and scientific domains, sparking growing interest recently. In this visionary paper, we embark on a comprehensive exploration of representative architectures to address the requirement. We highlight three pivotal paradigms: The state-of-the-art DL-centric architecture offloads DL computations to dedicated DL frameworks. The potential UDF-centric architecture encapsulates one or more tensor computations into User Defined Functions (UDFs) within the relational database management system (RDBMS). The potential relation-centric architecture aims to represent a large-scale tensor computation through relational operators. While each of these architectures demonstrates promise in specific use scenarios, we identify urgent requirements for seamless integration of these architectures and the middle ground in-between these architectures. We delve into the gaps that impede the integration and explore innovative strategies to close them. We present a pathway to establish a novel RDBMS for enabling a broad class of data-intensive DL inference applications., Comment: * Authors are ordered alphabetically; Jia Zou is the corresponding author

Existing approaches to automatic data transformation are insufficient to meet the requirements in many real-world scenarios, such as the building sector. First, there is no convenient interface for domain experts to provide domain knowledge easily. Second, they require significant training data collection overheads. Third, the accuracy suffers from complicated schema changes. To bridge this gap, we present a novel approach that leverages the unique capabilities of large language models (LLMs) in coding, complex reasoning, and zero-shot learning to generate SQL code that transforms the source datasets into the target datasets. We demonstrate the viability of this approach by designing an LLM-based framework, termed SQLMorpher, which comprises a prompt generator that integrates the initial prompt with optional domain knowledge and historical patterns in external databases. It also implements an iterative prompt optimization mechanism that automatically improves the prompt based on flaw detection. The key contributions of this work include (1) pioneering an end-to-end LLM-based solution for data transformation, (2) developing a benchmark dataset of 105 real-world building energy data transformation problems, and (3) conducting an extensive empirical evaluation where our approach achieved 96% accuracy in all 105 problems. SQLMorpher demonstrates the effectiveness of utilizing LLMs in complex, domain-specific challenges, highlighting the potential of their potential to drive sustainable solutions., Comment: 10 pages, 7 figures

Storing tabular data to balance storage and query efficiency is a long-standing research question in the database community. In this work, we argue and show that a novel DeepMapping abstraction, which relies on the impressive memorization capabilities of deep neural networks, can provide better storage cost, better latency, and better run-time memory footprint, all at the same time. Such unique properties may benefit a broad class of use cases in capacity-limited devices. Our proposed DeepMapping abstraction transforms a dataset into multiple key-value mappings and constructs a multi-tasking neural network model that outputs the corresponding values for a given input key. To deal with memorization errors, DeepMapping couples the learned neural network with a lightweight auxiliary data structure capable of correcting mistakes. The auxiliary structure design further enables DeepMapping to efficiently deal with insertions, deletions, and updates even without retraining the mapping. We propose a multi-task search strategy for selecting the hybrid DeepMapping structures (including model architecture and auxiliary structure) with a desirable trade-off among memorization capacity, size, and efficiency. Extensive experiments with a real-world dataset, synthetic and benchmark datasets, including TPC-H and TPC-DS, demonstrated that the DeepMapping approach can better balance the retrieving speed and compression ratio against several cutting-edge competitors.

Fast radio bursts (FRBs) have been found in great numbers, but the physical mechanism of these sources is still a mystery. The redshift evolutions of the FRB energy distribution function and the volumetric rate shed light on the origin of FRBs. However, such estimations rely on the dispersion measurement (DM)-redshift ($z$) relationship. A few FRBs that have been detected recently show large excess DMs beyond the expectation from the cosmological and Milky Way contributions, which indicates large spread of DMs from their host galaxies. In this work, we adopt two lognormal-distributed ${\rm DM}_{\rm host}$ models and estimate the energy function using the non-repeating FRBs selected from the Canadian Hydrogen Intensity Mapping Experiment (CHIME)/FRB Catalog 1. By comparing the lognormal-distributed ${\rm DM}_{\rm host}$ models to a constant ${\rm DM}_{\rm host}$ model, the FRB energy function results are consistent within the measurement uncertainty. We also estimate the volumetric rate of the non-repeating FRBs in three different redshift bins. The volumetric rate shows that the trend is consistent with the stellar-mass density redshift evolution. Since the lognormal-distributed ${\rm DM}_{\rm host}$ model increases the measurement errors, the inference of FRBs tracking the stellar-mass density is nonetheless undermined., Comment: 15 pages, 5 figures; published version

Decision forest, including RandomForest, XGBoost, and LightGBM, is one of the most popular machine learning techniques used in many industrial scenarios, such as credit card fraud detection, ranking, and business intelligence. Because the inference process is usually performance-critical, a number of frameworks were developed and dedicated for decision forest inference, such as ONNX, TreeLite from Amazon, TensorFlow Decision Forest from Google, HummingBird from Microsoft, Nvidia FIL, and lleaves. However, these frameworks are all decoupled with data management frameworks. It is unclear whether in-database inference will improve the overall performance. In addition, these frameworks used different algorithms, optimization techniques, and parallelism models. It is unclear how these implementations will affect the overall performance and how to make design decisions for an in-database inference framework. In this work, we investigated the above questions by comprehensively comparing the end-to-end performance of the aforementioned inference frameworks and netsDB, an in-database inference framework we implemented. Through this study, we identified that netsDB is best suited for handling small-scale models on large-scale datasets and all-scale models on small-scale datasets, for which it achieved up to hundreds of times of speedup. In addition, the relation-centric representation we proposed significantly improved netsDB's performance in handling large-scale models, while the model reuse optimization we proposed further improved netsDB's performance in handling small-scale datasets.

Non-Gaussian states (NGSs) with higher-order correlation properties have wide-range applications in quantum information processing. However, the generation of such states with high quality still faces practical challenges. Here, we propose a protocol to faithfully generate two types of mechanical NGSs, i.e., Schr\"{o}dinger cat states and Fock states, in open optomechanical systems, even when the cooperativity is smaller than one ($g^2/\kappa\gamma<1$). In contrast to the usual scheme, a short squeezed field is pumped to rapidly entangle with a mechanical resonator via a beam-splitter-like optomechanical interaction, effectively reducing the mechanical decoherence. Furthermore, by performing an additional amplifier and a following multi photon subtraction on the entangled optical field, one can selectively obtain the high-fidelity mechanical cat and Fock states. This protocol is robust to various imperfections, allowing it to be implemented with state-of-the-art experimental systems with close to unit fidelity. Moreover, it can be extended to generate a four-component cat state and provide possibilities for future quantum applications of NGSs., Comment: 7 pages, 4 figures with additional supplementary information (10 pages, 6 figures)

Deep learning has become the most popular direction in machine learning and artificial intelligence. However, the preparation of training data, as well as model training, are often time-consuming and become the bottleneck of the end-to-end machine learning lifecycle. Reusing models for inferring a dataset can avoid the costs of retraining. However, when there are multiple candidate models, it is challenging to discover the right model for reuse. Although there exist a number of model sharing platforms such as ModelDB, TensorFlow Hub, PyTorch Hub, and DLHub, most of these systems require model uploaders to manually specify the details of each model and model downloaders to screen keyword search results for selecting a model. We are lacking a highly productive model search tool that selects models for deployment without the need for any manual inspection and/or labeled data from the target domain. This paper proposes multiple model search strategies including various similarity-based approaches and non-similarity-based approaches. We design, implement, and evaluate these approaches on multiple model inference scenarios, including activity recognition, image recognition, text classification, natural language processing, and entity matching. The experimental evaluation showed that our proposed asymmetric similarity-based measurement, adaptivity, outperformed symmetric similarity-based measurements and non-similarity-based measurements in most of the workloads., Comment: arXiv admin note: text overlap with arXiv:2010.09474

There are significant benefits to serve deep learning models from relational databases. First, features extracted from databases do not need to be transferred to any decoupled deep learning systems for inferences, and thus the system management overhead can be significantly reduced. Second, in a relational database, data management along the storage hierarchy is fully integrated with query processing, and thus it can continue model serving even if the working set size exceeds the available memory. Applying model deduplication can greatly reduce the storage space, memory footprint, cache misses, and inference latency. However, existing data deduplication techniques are not applicable to the deep learning model serving applications in relational databases. They do not consider the impacts on model inference accuracy as well as the inconsistency between tensor blocks and database pages. This work proposed synergistic storage optimization techniques for duplication detection, page packing, and caching, to enhance database systems for model serving. We implemented the proposed approach in netsDB, an object-oriented relational database. Evaluation results show that our proposed techniques significantly improved the storage efficiency and the model inference latency, and serving models from relational databases outperformed existing deep learning frameworks when the working set size exceeds available memory.

Data is the king in the age of AI. However data integration is often a laborious task that is hard to automate. Schema change is one significant obstacle to the automation of the end-to-end data integration process. Although there exist mechanisms such as query discovery and schema modification language to handle the problem, these approaches can only work with the assumption that the schema is maintained by a database. However, we observe diversified schema changes in heterogeneous data and open data, most of which has no schema defined. In this work, we propose to use deep learning to automatically deal with schema changes through a super cell representation and automatic injection of perturbations to the training data to make the model robust to schema changes. Our experimental results demonstrate that our proposed approach is effective for two real-world data integration scenarios: coronavirus data integration, and machine log integration., Comment: In submission

In recent, deep learning has become the most popular direction in machine learning and artificial intelligence. However, preparation of training data is often a bottleneck in the lifecycle of deploying a deep learning model for production or research. Reusing models for inferencing a dataset can greatly save the human costs required for training data creation. Although there exist a number of model sharing platform such as TensorFlow Hub, PyTorch Hub, DLHub, most of these systems require model uploaders to manually specify the details of each model and model downloaders to screen keyword search results for selecting a model. They are in lack of an automatic model searching tool. This paper proposes an end-to-end process of searching related models for serving based on the similarity of the target dataset and the training datasets of the available models. While there exist many similarity measurements, we study how to efficiently apply these metrics without pair-wise comparison and compare the effectiveness of these metrics. We find that our proposed adaptivity measurement which is based on Jensen-Shannon (JS) divergence, is an effective measurement, and its computation can be significantly accelerated by using the technique of locality sensitive hashing.

We consider the question: what is the abstraction that should be implemented by the computational engine of a machine learning system? Current machine learning systems typically push whole tensors through a series of compute kernels such as matrix multiplications or activation functions, where each kernel runs on an AI accelerator (ASIC) such as a GPU. This implementation abstraction provides little built-in support for ML systems to scale past a single machine, or for handling large models with matrices or tensors that do not easily fit into the RAM of an ASIC. In this paper, we present an alternative implementation abstraction called the tensor relational algebra (TRA). The TRA is a set-based algebra based on the relational algebra. Expressions in the TRA operate over binary tensor relations, where keys are multi-dimensional arrays and values are tensors. The TRA is easily executed with high efficiency in a parallel or distributed environment, and amenable to automatic optimization. Our empirical study shows that the optimized TRA-based back-end can significantly outperform alternatives for running ML workflows in distributed clusters.

Persistent partitioning is effective in avoiding expensive shuffling operations. However it remains a significant challenge to automate this process for Big Data analytics workloads that extensively use user defined functions (UDFs), where sub-computations are hard to be reused for partitionings compared to relational applications. In addition, functional dependency that is widely utilized for partitioning selection is often unavailable in the unstructured data that is ubiquitous in UDF-centric analytics. We propose the Lachesis system, which represents UDF-centric workloads as workflows of analyzable and reusable sub-computations. Lachesis further adopts a deep reinforcement learning model to infer which sub-computations should be used to partition the underlying data. This analysis is then applied to automatically optimize the storage of the data across applications to improve the performance and users' productivity., Comment: In submission

A number of popular systems, most notably Google's TensorFlow, have been implemented from the ground up to support machine learning tasks. We consider how to make a very small set of changes to a modern relational database management system (RDBMS) to make it suitable for distributed learning computations. Changes include adding better support for recursion, and optimization and execution of very large compute plans. We also show that there are key advantages to using an RDBMS as a machine learning platform. In particular, learning based on a database management system allows for trivial scaling to large data sets and especially large models, where different computational units operate on different parts of a model that may be too large to fit into RAM.

Storage and memory systems for modern data analytics are heavily layered, managing shared persistent data, cached data, and non-shared execution data in separate systems such as distributed file system like HDFS, in-memory file system like Alluxio and computation framework like Spark. Such layering introduces significant performance and management costs for copying data across layers redundantly and deciding proper resource allocation for all layers. In this paper we propose a single system called Pangea that can manage all data---both intermediate and long-lived data, and their buffer/caching, data placement optimization, and failure recovery---all in one monolithic storage system, without any layering. We present a detailed performance evaluation of Pangea and show that its performance compares favorably with several widely used layered systems such as Spark., Comment: 14 pages

This paper describes PlinyCompute, a system for development of high-performance, data-intensive, distributed computing tools and libraries. In the large, PlinyCompute presents the programmer with a very high-level, declarative interface, relying on automatic, relational-database style optimization to figure out how to stage distributed computations. However, in the small, PlinyCompute presents the capable systems programmer with a persistent object data model and API (the "PC object model") and associated memory management system that has been designed from the ground-up for high performance, distributed, data-intensive computing. This contrasts with most other Big Data systems, which are constructed on top of the Java Virtual Machine (JVM), and hence must at least partially cede performance-critical concerns such as memory management (including layout and de/allocation) and virtual method/function dispatch to the JVM. This hybrid approach---declarative in the large, trusting the programmer's ability to utilize PC object model efficiently in the small---results in a system that is ideal for the development of reusable, data-intensive tools and libraries. Through extensive benchmarking, we show that implementing complex objects manipulation and non-trivial, library-style computations on top of PlinyCompute can result in a speedup of 2x to more than 50x or more compared to equivalent implementations on Spark., Comment: 48 pages, including references and Appendix