Search

This paper introduces a novel reinforcement learning (RL) strategy designed to facilitate rapid autonomy transfer by utilizing pre-trained critic value functions from multiple environments. Unlike traditional methods that require extensive retraining or fine-tuning, our approach integrates existing knowledge, enabling an RL agent to adapt swiftly to new settings without requiring extensive computational resources. Our contributions include development of the Multi-Critic Actor-Critic (MCAC) algorithm, establishing its convergence, and empirical evidence demonstrating its efficacy. Our experimental results show that MCAC significantly outperforms the baseline actor-critic algorithm, achieving up to 22.76x faster autonomy transfer and higher reward accumulation. This advancement underscores the potential of leveraging accumulated knowledge for efficient adaptation in RL applications.

The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to train or fine-tune these LLMs is often undisclosed, allowing an attacker to compromise the data and inject backdoors into the models. In this paper, we develop a novel inference time defense, named CleanGen, to mitigate backdoor attacks for generation tasks in LLMs. CleanGenis a lightweight and effective decoding strategy that is compatible with the state-of-the-art (SOTA) LLMs. Our insight behind CleanGen is that compared to other LLMs, backdoored LLMs assign significantly higher probabilities to tokens representing the attacker-desired contents. These discrepancies in token probabilities enable CleanGen to identify suspicious tokens favored by the attacker and replace them with tokens generated by another LLM that is not compromised by the same attacker, thereby avoiding generation of attacker-desired content. We evaluate CleanGen against five SOTA backdoor attacks. Our results show that CleanGen achieves lower attack success rates (ASR) compared to five SOTA baseline defenses for all five backdoor attacks. Moreover, LLMs deploying CleanGen maintain helpfulness in their responses when serving benign user queries with minimal added computational overhead.

Large language models (LLMs) are expected to follow instructions from users and engage in conversations. Techniques to enhance LLMs' instruction-following capabilities typically fine-tune them using data structured according to a predefined chat template. Although chat templates are shown to be effective in optimizing LLM performance, their impact on safety alignment of LLMs has been less understood, which is crucial for deploying LLMs safely at scale. In this paper, we investigate how chat templates affect safety alignment of LLMs. We identify a common vulnerability, named ChatBug, that is introduced by chat templates. Our key insight to identify ChatBug is that the chat templates provide a rigid format that need to be followed by LLMs, but not by users. Hence, a malicious user may not necessarily follow the chat template when prompting LLMs. Instead, malicious users could leverage their knowledge of the chat template and accordingly craft their prompts to bypass safety alignments of LLMs. We develop two attacks to exploit the ChatBug vulnerability. We demonstrate that a malicious user can exploit the ChatBug vulnerability of eight state-of-the-art (SOTA) LLMs and effectively elicit unintended responses from these models. Moreover, we show that ChatBug can be exploited by existing jailbreak attacks to enhance their attack success rates. We investigate potential countermeasures to ChatBug. Our results show that while adversarial training effectively mitigates the ChatBug vulnerability, the victim model incurs significant performance degradation. These results highlight the trade-off between safety alignment and helpfulness. Developing new methods for instruction tuning to balance this trade-off is an open and critical direction for future research

High-quality instruction data is critical for aligning large language models (LLMs). Although some models, such as Llama-3-Instruct, have open weights, their alignment data remain private, which hinders the democratization of AI. High human labor costs and a limited, predefined scope for prompting prevent existing open-source data creation methods from scaling effectively, potentially limiting the diversity and quality of public alignment datasets. Is it possible to synthesize high-quality instruction data at scale by extracting it directly from an aligned LLM? We present a self-synthesis method for generating large-scale alignment data named Magpie. Our key observation is that aligned LLMs like Llama-3-Instruct can generate a user query when we input only the left-side templates up to the position reserved for user messages, thanks to their auto-regressive nature. We use this method to prompt Llama-3-Instruct and generate 4 million instructions along with their corresponding responses. We perform a comprehensive analysis of the extracted data and select 300K high-quality instances. To compare Magpie data with other public instruction datasets, we fine-tune Llama-3-8B-Base with each dataset and evaluate the performance of the fine-tuned models. Our results indicate that in some tasks, models fine-tuned with Magpie perform comparably to the official Llama-3-8B-Instruct, despite the latter being enhanced with 10 million data points through supervised fine-tuning (SFT) and subsequent feedback learning. We also show that using Magpie solely for SFT can surpass the performance of previous public datasets utilized for both SFT and preference optimization, such as direct preference optimization with UltraFeedback. This advantage is evident on alignment benchmarks such as AlpacaEval, ArenaHard, and WildBench., Comment: Link: https://magpie-align.github.io/

In Federated Learning (FL), a set of clients collaboratively train a machine learning model (called global model) without sharing their local training data. The local training data of clients is typically non-i.i.d. and heterogeneous, resulting in varying contributions from individual clients to the final performance of the global model. In response, many contribution evaluation methods were proposed, where the server could evaluate the contribution made by each client and incentivize the high-contributing clients to sustain their long-term participation in FL. Existing studies mainly focus on developing new metrics or algorithms to better measure the contribution of each client. However, the security of contribution evaluation methods of FL operating in adversarial environments is largely unexplored. In this paper, we propose the first model poisoning attack on contribution evaluation methods in FL, termed ACE. Specifically, we show that any malicious client utilizing ACE could manipulate the parameters of its local model such that it is evaluated to have a high contribution by the server, even when its local training data is indeed of low quality. We perform both theoretical analysis and empirical evaluations of ACE. Theoretically, we show our design of ACE can effectively boost the malicious client's perceived contribution when the server employs the widely-used cosine distance metric to measure contribution. Empirically, our results show ACE effectively and efficiently deceive five state-of-the-art contribution evaluation methods. In addition, ACE preserves the accuracy of the final global models on testing inputs. We also explore six countermeasures to defend ACE. Our results show they are inadequate to thwart ACE, highlighting the urgent need for new defenses to safeguard the contribution evaluation methods in FL., Comment: To appear in the 33rd USENIX Security Symposium, 2024

Safety is a fundamental requirement of many robotic systems. Control barrier function (CBF)-based approaches have been proposed to guarantee the safety of robotic systems. However, the effectiveness of these approaches highly relies on the choice of CBFs. Inspired by the universal approximation power of neural networks, there is a growing trend toward representing CBFs using neural networks, leading to the notion of neural CBFs (NCBFs). Current NCBFs, however, are trained and deployed in benign environments, making them ineffective for scenarios where robotic systems experience sensor faults and attacks. In this paper, we study safety-critical control synthesis for robotic systems under sensor faults and attacks. Our main contribution is the development and synthesis of a new class of CBFs that we term fault tolerant neural control barrier function (FT-NCBF). We derive the necessary and sufficient conditions for FT-NCBFs to guarantee safety, and develop a data-driven method to learn FT-NCBFs by minimizing a loss function constructed using the derived conditions. Using the learned FT-NCBF, we synthesize a control input and formally prove the safety guarantee provided by our approach. We demonstrate our proposed approach using two case studies: obstacle avoidance problem for an autonomous mobile robot and spacecraft rendezvous problem, with code available via https://github.com/HongchaoZhang-HZ/FTNCBF.

Safety is critical to the usage of large language models (LLMs). Multiple techniques such as data filtering and supervised fine-tuning have been developed to strengthen LLM safety. However, currently known techniques presume that corpora used for safety alignment of LLMs are solely interpreted by semantics. This assumption, however, does not hold in real-world applications, which leads to severe vulnerabilities in LLMs. For example, users of forums often use ASCII art, a form of text-based art, to convey image information. In this paper, we propose a novel ASCII art-based jailbreak attack and introduce a comprehensive benchmark Vision-in-Text Challenge (ViTC) to evaluate the capabilities of LLMs in recognizing prompts that cannot be solely interpreted by semantics. We show that five SOTA LLMs (GPT-3.5, GPT-4, Gemini, Claude, and Llama2) struggle to recognize prompts provided in the form of ASCII art. Based on this observation, we develop the jailbreak attack ArtPrompt, which leverages the poor performance of LLMs in recognizing ASCII art to bypass safety measures and elicit undesired behaviors from LLMs. ArtPrompt only requires black-box access to the victim LLMs, making it a practical attack. We evaluate ArtPrompt on five SOTA LLMs, and show that ArtPrompt can effectively and efficiently induce undesired behaviors from all five LLMs. Our code is available at https://github.com/uw-nsl/ArtPrompt., Comment: To appear in ACL 2024

As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety. Jailbreak attacks, aiming to provoke unintended and unsafe behaviors from LLMs, remain a significant/leading LLM safety threat. In this paper, we aim to defend LLMs against jailbreak attacks by introducing SafeDecoding, a safety-aware decoding strategy for LLMs to generate helpful and harmless responses to user queries. Our insight in developing SafeDecoding is based on the observation that, even though probabilities of tokens representing harmful contents outweigh those representing harmless responses, safety disclaimers still appear among the top tokens after sorting tokens by probability in descending order. This allows us to mitigate jailbreak attacks by identifying safety disclaimers and amplifying their token probabilities, while simultaneously attenuating the probabilities of token sequences that are aligned with the objectives of jailbreak attacks. We perform extensive experiments on five LLMs using six state-of-the-art jailbreak attacks and four benchmark datasets. Our results show that SafeDecoding significantly reduces the attack success rate and harmfulness of jailbreak attacks without compromising the helpfulness of responses to benign user queries. SafeDecoding outperforms six defense methods., Comment: To appear in ACL 2024

We propose and analyze an adaptive adversary that can retrain a Trojaned DNN and is also aware of SOTA output-based Trojaned model detectors. We show that such an adversary can ensure (1) high accuracy on both trigger-embedded and clean samples and (2) bypass detection. Our approach is based on an observation that the high dimensionality of the DNN parameters provides sufficient degrees of freedom to simultaneously achieve these objectives. We also enable SOTA detectors to be adaptive by allowing retraining to recalibrate their parameters, thus modeling a co-evolution of parameters of a Trojaned model and detectors. We then show that this co-evolution can be modeled as an iterative game, and prove that the resulting (optimal) solution of this interactive game leads to the adversary successfully achieving the above objectives. In addition, we provide a greedy algorithm for the adversary to select a minimum number of input samples for embedding triggers. We show that for cross-entropy or log-likelihood loss functions used by the DNNs, the greedy algorithm provides provable guarantees on the needed number of trigger-embedded input samples. Extensive experiments on four diverse datasets -- MNIST, CIFAR-10, CIFAR-100, and SpeechCommand -- reveal that the adversary effectively evades four SOTA output-based Trojaned model detectors: MNTD, NeuralCleanse, STRIP, and TABOR.

Transfer learning (TL) has been demonstrated to improve DNN model performance when faced with a scarcity of training samples. However, the suitability of TL as a solution to reduce vulnerability of overfitted DNNs to privacy attacks is unexplored. A class of privacy attacks called membership inference attacks (MIAs) aim to determine whether a given sample belongs to the training dataset (member) or not (nonmember). We introduce Double-Dip, a systematic empirical study investigating the use of TL (Stage-1) combined with randomization (Stage-2) to thwart MIAs on overfitted DNNs without degrading classification accuracy. Our study examines the roles of shared feature space and parameter values between source and target models, number of frozen layers, and complexity of pretrained models. We evaluate Double-Dip on three (Target, Source) dataset paris: (i) (CIFAR-10, ImageNet), (ii) (GTSRB, ImageNet), (iii) (CelebA, VGGFace2). We consider four publicly available pretrained DNNs: (a) VGG-19, (b) ResNet-18, (c) Swin-T, and (d) FaceNet. Our experiments demonstrate that Stage-1 reduces adversary success while also significantly increasing classification accuracy of nonmembers against an adversary with either white-box or black-box DNN model access, attempting to carry out SOTA label-only MIAs. After Stage-2, success of an adversary carrying out a label-only MIA is further reduced to near 50%, bringing it closer to a random guess and showing the effectiveness of Double-Dip. Stage-2 of Double-Dip also achieves lower ASR and higher classification accuracy than regularization and differential privacy-based methods.

Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting, particularly when tackling tasks that require systematic reasoning processes. On the other hand, COT prompting also poses new vulnerabilities in the form of backdoor attacks, wherein the model will output unintended malicious content under specific backdoor-triggered conditions during inference. Traditional methods for launching backdoor attacks involve either contaminating the training dataset with backdoored instances or directly manipulating the model parameters during deployment. However, these approaches are not practical for commercial LLMs that typically operate via API access. In this paper, we propose BadChain, the first backdoor attack against LLMs employing COT prompting, which does not require access to the training dataset or model parameters and imposes low computational overhead. BadChain leverages the inherent reasoning capabilities of LLMs by inserting a backdoor reasoning step into the sequence of reasoning steps of the model output, thereby altering the final response when a backdoor trigger exists in the query prompt. Empirically, we show the effectiveness of BadChain for two COT strategies across four LLMs (Llama2, GPT-3.5, PaLM2, and GPT-4) and six complex benchmark tasks encompassing arithmetic, commonsense, and symbolic reasoning. Moreover, we show that LLMs endowed with stronger reasoning capabilities exhibit higher susceptibility to BadChain, exemplified by a high average attack success rate of 97.0% across the six benchmark tasks on GPT-4. Finally, we propose two defenses based on shuffling and demonstrate their overall ineffectiveness against BadChain. Therefore, BadChain remains a severe threat to LLMs, underscoring the urgency for the development of robust and effective future defenses., Comment: Accepted to ICLR2024

Federated learning (FL) enables multiple participants to train a global machine learning model without sharing their private training data. Peer-to-peer (P2P) FL advances existing centralized FL paradigms by eliminating the server that aggregates local models from participants and then updates the global model. However, P2P FL is vulnerable to (i) honest-but-curious participants whose objective is to infer private training data of other participants, and (ii) Byzantine participants who can transmit arbitrarily manipulated local models to corrupt the learning process. P2P FL schemes that simultaneously guarantee Byzantine resilience and preserve privacy have been less studied. In this paper, we develop Brave, a protocol that ensures Byzantine Resilience And privacy-preserving property for P2P FL in the presence of both types of adversaries. We show that Brave preserves privacy by establishing that any honest-but-curious adversary cannot infer other participants' private data by observing their models. We further prove that Brave is Byzantine-resilient, which guarantees that all benign participants converge to an identical model that deviates from a global model trained without Byzantine adversaries by a bounded distance. We evaluate Brave against three state-of-the-art adversaries on a P2P FL for image classification tasks on benchmark datasets CIFAR10 and MNIST. Our results show that the global model learned with Brave in the presence of adversaries achieves comparable classification accuracy to a global model trained in the absence of any adversary.