arXiv subjects

Andy Zhou

Publications and source records attributed to Andy Zhou.

At least 19 recordsLinked to original sources

arXiv2025

GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs

As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted significant societal and regulatory concerns. In response, governments have issued ethics guidelines to promote the development of trustworthy AI. However, these guidelines are typically high-level demands for developers and testers, leaving a gap in translating them into actionable testing questions to verify LLM compliance. To address this challenge, we introduce GUARD (Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics), a testing method designed to operationalize guidelines into specific guideline-violating questions that assess LLM adherence. To implement this, GUARD uses automated generation of guideline-violating questions based on government-issued guidelines, thereby testing whether responses comply with these guidelines. When responses directly violate guidelines, GUARD reports inconsistencies. Furthermore, for responses that do not directly violate guidelines, GUARD integrates the concept of ``jailbreaks'' to diagnostics, named GUARD-JD, which creates scenarios that provoke unethical or guideline-violating responses, effectively identifying potential scenarios that could bypass built-in safety mechanisms. Our method finally culminates in a compliance report, delineating the extent of adherence and highlighting any violations. We empirically validated the effectiveness of GUARD on eight LLMs, including Vicuna-13B, LongChat-7B, Llama2-7B, Llama-3-8B, GPT-3.5, GPT-4, GPT-4o, and Claude-3.7, by testing compliance under three government-issued guidelines and conducting jailbreak diagnostics. Additionally, GUARD-JD can transfer jailbreak diagnostics to vision-language models (MiniGPT-v2 and Gemini-1.5), demonstrating its usage in promoting reliable LLM-based applications.

cs.CL↗

arXiv2025

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

As large language models (LLMs) become increasingly capable, security and safety evaluation are crucial. While current red teaming approaches have made strides in assessing LLM vulnerabilities, they often rely heavily on human input and lack comprehensive coverage of emerging attack vectors. This paper introduces AutoRedTeamer, a novel framework for fully automated, end-to-end red teaming against LLMs. AutoRedTeamer combines a multi-agent architecture with a memory-guided attack selection mechanism to enable continuous discovery and integration of new attack vectors. The dual-agent framework consists of a red teaming agent that can operate from high-level risk categories alone to generate and execute test cases and a strategy proposer agent that autonomously discovers and implements new attacks by analyzing recent research. This modular design allows AutoRedTeamer to adapt to emerging threats while maintaining strong performance on existing attack vectors. We demonstrate AutoRedTeamer's effectiveness across diverse evaluation settings, achieving 20% higher attack success rates on HarmBench against Llama-3.1-70B while reducing computational costs by 46% compared to existing approaches. AutoRedTeamer also matches the diversity of human-curated benchmarks in generating test cases, providing a comprehensive, scalable, and continuously evolving framework for evaluating the security of AI systems.

cs.CR↗

arXiv2025

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Multimodal foundation models (MMFMs) play a crucial role in various applications, including autonomous driving, healthcare, and virtual assistants. However, several studies have revealed vulnerabilities in these models, such as generating unsafe content by text-to-image models. Existing benchmarks on multimodal models either predominantly assess the helpfulness of these models, or only focus on limited perspectives such as fairness and privacy. In this paper, we present the first unified platform, MMDT (Multimodal DecodingTrust), designed to provide a comprehensive safety and trustworthiness evaluation for MMFMs. Our platform assesses models from multiple perspectives, including safety, hallucination, fairness/bias, privacy, adversarial robustness, and out-of-distribution (OOD) generalization. We have designed various evaluation scenarios and red teaming algorithms under different tasks for each perspective to generate challenging data, forming a high-quality benchmark. We evaluate a range of multimodal models using MMDT, and our findings reveal a series of vulnerabilities and areas for improvement across these perspectives. This work introduces the first comprehensive and unique safety and trustworthiness evaluation platform for MMFMs, paving the way for developing safer and more reliable MMFMs and systems. Our platform and benchmark are available at https://mmdecodingtrust.github.io/.

cs.CL↗

arXiv2025

Compositional Subspace Representation Fine-tuning for Adaptive Large Language Models

Adapting large language models to multiple tasks can cause cross-skill interference, where improvements for one skill degrade another. While methods such as LoRA impose orthogonality constraints at the weight level, they do not fully address interference in hidden-state representations. We propose Compositional Subspace Representation Fine-tuning (CS-ReFT), a novel representation-based approach that learns multiple orthonormal subspace transformations, each specializing in a distinct skill, and composes them via a lightweight router. By isolating these subspace edits in the hidden state, rather than weight matrices, CS-ReFT prevents cross-task conflicts more effectively. On the AlpacaEval benchmark, applying CS-ReFT to Llama-2-7B achieves a 93.94% win rate, surpassing GPT-3.5 Turbo (86.30%) while requiring only 0.0098% of model parameters. These findings show that specialized representation edits, composed via a simple router, significantly enhance multi-task instruction following with minimal overhead.

cs.CL↗

arXiv2025

Tempest: Autonomous Multi-Turn Jailbreaking of Large Language Models with Tree Search

We introduce Tempest, a multi-turn adversarial framework that models the gradual erosion of Large Language Model (LLM) safety through a tree search perspective. Unlike single-turn jailbreaks that rely on one meticulously engineered prompt, Tempest expands the conversation at each turn in a breadth-first fashion, branching out multiple adversarial prompts that exploit partial compliance from previous responses. By tracking these incremental policy leaks and re-injecting them into subsequent queries, Tempest reveals how minor concessions can accumulate into fully disallowed outputs. Evaluations on the JailbreakBench dataset show that Tempest achieves a 100% success rate on GPT-3.5-turbo and 97% on GPT-4 in a single multi-turn run, using fewer queries than baselines such as Crescendo or GOAT. This tree search methodology offers an in-depth view of how model safeguards degrade over successive dialogue turns, underscoring the urgency of robust multi-turn testing procedures for language models.

cs.AI↗

arXiv2024

RedCode: Risky Code Execution and Generation Benchmark for Code Agents

With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant barriers to the real-world deployment of these agents. To provide comprehensive and practical evaluations on the safety of code agents, we propose RedCode, a benchmark for risky code execution and generation: (1) RedCode-Exec provides challenging prompts that could lead to risky code execution, aiming to evaluate code agents' ability to recognize and handle unsafe code. We provide a total of 4,050 risky test cases in Python and Bash tasks with diverse input formats including code snippets and natural text. They covers 25 types of critical vulnerabilities spanning 8 domains (e.g., websites, file systems). We provide Docker environments and design corresponding evaluation metrics to assess their execution results. (2) RedCode-Gen provides 160 prompts with function signatures and docstrings as input to assess whether code agents will follow instructions to generate harmful code or software. Our empirical findings, derived from evaluating three agent frameworks based on 19 LLMs, provide insights into code agents' vulnerabilities. For instance, evaluations on RedCode-Exec show that agents are more likely to reject executing risky operations on the operating system, but are less likely to reject executing technically buggy code, indicating high risks. Risky operations described in natural text lead to a lower rejection rate than those in code format. Additionally, evaluations on RedCode-Gen show that more capable base models and agents with stronger overall coding abilities, such as GPT4, tend to produce more sophisticated and effective harmful software. Our findings highlight the need for stringent safety evaluations for diverse code agents. Our dataset and code are available at https://github.com/AI-secure/RedCode.

cs.SE↗

arXiv2024

Estimating Broad Sense Heritability via Kernel Ridge Regression

The broad sense genetic heritability, which quantifies the total proportion of phenotypic variation in a population due to genetic factors, is crucial for understanding trait inheritance. While many existing methods focus on estimating narrow sense heritability, which accounts only for additive genetic variation, this paper introduces a kernel ridge regression approach to estimate broad-sense heritability. We provide both upper and lower bounds for the estimator. The effectiveness of the proposed method was evaluated through extensive simulations of both synthetic data and real data from the 1000 Genomes Project. Additionally, the estimator was applied to data from the Alzheimer's Disease Neuroimaging Initiative to demonstrate its practical utility.

stat.ME↗

arXiv2024

KnowGraph: Knowledge-Enabled Anomaly Detection via Logical Reasoning on Graph Data

Graph-based anomaly detection is pivotal in diverse security applications, such as fraud detection in transaction networks and intrusion detection for network traffic. Standard approaches, including Graph Neural Networks (GNNs), often struggle to generalize across shifting data distributions. Meanwhile, real-world domain knowledge is more stable and a common existing component of real-world detection strategies. To explicitly integrate such knowledge into data-driven models such as GCNs, we propose KnowGraph, which integrates domain knowledge with data-driven learning for enhanced graph-based anomaly detection. KnowGraph comprises two principal components: (1) a statistical learning component that utilizes a main model for the overarching detection task, augmented by multiple specialized knowledge models that predict domain-specific semantic entities; (2) a reasoning component that employs probabilistic graphical models to execute logical inferences based on model outputs, encoding domain knowledge through weighted first-order logic formulas. Extensive experiments on these large-scale real-world datasets show that KnowGraph consistently outperforms state-of-the-art baselines in both transductive and inductive settings, achieving substantial gains in average precision when generalizing to completely unseen test graphs. Further ablation studies demonstrate the effectiveness of the proposed reasoning component in improving detection performance, especially under extreme class imbalance. These results highlight the potential of integrating domain knowledge into data-driven models for high-stakes, graph-based security applications.

cs.CR↗

arXiv2024

Tamper-Resistant Safeguards for Open-Weight LLMs

Rapid advances in the capabilities of large language models (LLMs) have raised widespread concerns regarding their potential for malicious use. Open-weight LLMs present unique challenges, as existing safeguards lack robustness to tampering attacks that modify model weights. For example, recent works have demonstrated that refusal and unlearning safeguards can be trivially removed with a few steps of fine-tuning. These vulnerabilities necessitate new approaches for enabling the safe release of open-weight LLMs. We develop a method, called TAR, for building tamper-resistant safeguards into open-weight LLMs such that adversaries cannot remove the safeguards even after hundreds of steps of fine-tuning. In extensive evaluations and red teaming analyses, we find that our method greatly improves tamper-resistance while preserving benign capabilities. Our results demonstrate that progress on tamper-resistance is possible, opening up a promising new avenue to improve the safety and security of open-weight LLMs.

cs.LG↗

arXiv2024

AIR-Bench 2024: A Safety Benchmark Based on Risk Categories from Regulations and Policies

Foundation models (FMs) provide societal benefits but also amplify risks. Governments, companies, and researchers have proposed regulatory frameworks, acceptable use policies, and safety benchmarks in response. However, existing public benchmarks often define safety categories based on previous literature, intuitions, or common sense, leading to disjointed sets of categories for risks specified in recent regulations and policies, which makes it challenging to evaluate and compare FMs across these benchmarks. To bridge this gap, we introduce AIR-Bench 2024, the first AI safety benchmark aligned with emerging government regulations and company policies, following the regulation-based safety categories grounded in our AI risks study, AIR 2024. AIR 2024 decomposes 8 government regulations and 16 company policies into a four-tiered safety taxonomy with 314 granular risk categories in the lowest tier. AIR-Bench 2024 contains 5,694 diverse prompts spanning these categories, with manual curation and human auditing to ensure quality. We evaluate leading language models on AIR-Bench 2024, uncovering insights into their alignment with specified safety concerns. By bridging the gap between public benchmarks and practical AI risks, AIR-Bench 2024 provides a foundation for assessing model safety across jurisdictions, fostering the development of safer and more responsible AI systems.

cs.CY↗

arXiv2024

AI Risk Categorization Decoded (AIR 2024): From Government Regulations to Corporate Policies

We present a comprehensive AI risk taxonomy derived from eight government policies from the European Union, United States, and China and 16 company policies worldwide, making a significant step towards establishing a unified language for generative AI safety evaluation. We identify 314 unique risk categories organized into a four-tiered taxonomy. At the highest level, this taxonomy encompasses System & Operational Risks, Content Safety Risks, Societal Risks, and Legal & Rights Risks. The taxonomy establishes connections between various descriptions and approaches to risk, highlighting the overlaps and discrepancies between public and private sector conceptions of risk. By providing this unified framework, we aim to advance AI safety through information sharing across sectors and the promotion of best practices in risk mitigation for generative AI models and systems.

cs.CY↗

arXiv2024

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters

Large Language Models (LLMs) are typically harmless but remain vulnerable to carefully crafted prompts known as ``jailbreaks'', which can bypass protective measures and induce harmful behavior. Recent advancements in LLMs have incorporated moderation guardrails that can filter outputs, which trigger processing errors for certain malicious questions. Existing red-teaming benchmarks often neglect to include questions that trigger moderation guardrails, making it difficult to evaluate jailbreak effectiveness. To address this issue, we introduce JAMBench, a harmful behavior benchmark designed to trigger and evaluate moderation guardrails. JAMBench involves 160 manually crafted instructions covering four major risk categories at multiple severity levels. Furthermore, we propose a jailbreak method, JAM (Jailbreak Against Moderation), designed to attack moderation guardrails using jailbreak prefixes to bypass input-level filters and a fine-tuned shadow model functionally equivalent to the guardrail model to generate cipher characters to bypass output-level filters. Our extensive experiments on four LLMs demonstrate that JAM achieves higher jailbreak success ($\sim$ $\times$ 19.88) and lower filtered-out rates ($\sim$ $\times$ 1/6) than baselines.

cs.CR↗

arXiv2024

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning

Standard federated learning approaches suffer when client data distributions have sufficient heterogeneity. Recent methods addressed the client data heterogeneity issue via personalized federated learning (PFL) - a class of FL algorithms aiming to personalize learned global knowledge to better suit the clients' local data distributions. Existing PFL methods usually decouple global updates in deep neural networks by performing personalization on particular layers (i.e. classifier heads) and global aggregation for the rest of the network. However, preselecting network layers for personalization may result in suboptimal storage of global knowledge. In this work, we propose FedSelect, a novel PFL algorithm inspired by the iterative subnetwork discovery procedure used for the Lottery Ticket Hypothesis. FedSelect incrementally expands subnetworks to personalize client parameters, concurrently conducting global aggregations on the remaining parameters. This approach enables the personalization of both client parameters and subnetwork structure during the training process. Finally, we show that FedSelect outperforms recent state-of-the-art PFL algorithms under challenging client data heterogeneity settings and demonstrates robustness to various real-world distributional shifts. Our code is available at https://github.com/lapisrocks/fedselect.

cs.LG↗

arXiv2024

GUARD: Role-playing to Generate Natural-language Jailbreakings to Test Guideline Adherence of Large Language Models

The discovery of "jailbreaks" to bypass safety filters of Large Language Models (LLMs) and harmful responses have encouraged the community to implement safety measures. One major safety measure is to proactively test the LLMs with jailbreaks prior to the release. Therefore, such testing will require a method that can generate jailbreaks massively and efficiently. In this paper, we follow a novel yet intuitive strategy to generate jailbreaks in the style of the human generation. We propose a role-playing system that assigns four different roles to the user LLMs to collaborate on new jailbreaks. Furthermore, we collect existing jailbreaks and split them into different independent characteristics using clustering frequency and semantic patterns sentence by sentence. We organize these characteristics into a knowledge graph, making them more accessible and easier to retrieve. Our system of different roles will leverage this knowledge graph to generate new jailbreaks, which have proved effective in inducing LLMs to generate unethical or guideline-violating responses. In addition, we also pioneer a setting in our system that will automatically follow the government-issued guidelines to generate jailbreaks to test whether LLMs follow the guidelines accordingly. We refer to our system as GUARD (Guideline Upholding through Adaptive Role-play Diagnostics). We have empirically validated the effectiveness of GUARD on three cutting-edge open-sourced LLMs (Vicuna-13B, LongChat-7B, and Llama-2-7B), as well as a widely-utilized commercial LLM (ChatGPT). Moreover, our work extends to the realm of vision language models (MiniGPT-v2 and Gemini Vision Pro), showcasing GUARD's versatility and contributing valuable insights for the development of safer, more reliable LLM-based applications across diverse modalities.

cs.LG↗

arXiv2024

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks

Despite advances in AI alignment, large language models (LLMs) remain vulnerable to adversarial attacks or jailbreaking, in which adversaries can modify prompts to induce unwanted behavior. While some defenses have been proposed, they have not been adapted to newly proposed attacks and more challenging threat models. To address this, we propose an optimization-based objective for defending LLMs against jailbreaking attacks and an algorithm, Robust Prompt Optimization (RPO) to create robust system-level defenses. Our approach directly incorporates the adversary into the defensive objective and optimizes a lightweight and transferable suffix, enabling RPO to adapt to worst-case adaptive attacks. Our theoretical and experimental results show improved robustness to both jailbreaks seen during optimization and unknown jailbreaks, reducing the attack success rate (ASR) on GPT-4 to 6% and Llama-2 to 0% on JailbreakBench, setting the state-of-the-art. Code can be found at https://github.com/lapisrocks/rpo

cs.LG↗

arXiv2023

Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models

We propose a conceptually simple and lightweight framework for improving the robustness of vision models through the combination of knowledge distillation and data augmentation. We address the conjecture that larger models do not make for better teachers by showing strong gains in out-of-distribution robustness when distilling from pretrained foundation models. Following this finding, we propose Discrete Adversarial Distillation (DAD), which leverages a robust teacher to generate adversarial examples and a VQGAN to discretize them, creating more informative samples than standard data augmentation techniques. We provide a theoretical framework for the use of a robust teacher in the knowledge distillation with data augmentation setting and demonstrate strong gains in out-of-distribution robustness and clean accuracy across different student architectures. Notably, our method adds minor computational overhead compared to similar techniques and can be easily combined with other data augmentations for further improvements.

cs.LG↗

arXiv2023

Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models

While language models (LMs) have shown potential across a range of decision-making tasks, their reliance on simple acting processes limits their broad deployment as autonomous agents. In this paper, we introduce Language Agent Tree Search (LATS) -- the first general framework that synergizes the capabilities of LMs in reasoning, acting, and planning. By leveraging the in-context learning ability of LMs, we integrate Monte Carlo Tree Search into LATS to enable LMs as agents, along with LM-powered value functions and self-reflections for proficient exploration and enhanced decision-making. A key feature of our approach is the incorporation of an environment for external feedback, which offers a more deliberate and adaptive problem-solving mechanism that surpasses the constraints of existing techniques. Our experimental evaluation across diverse domains, including programming, interactive question-answering (QA), web navigation, and math, validates the effectiveness and generality of LATS in decision-making while maintaining competitive or improved reasoning performance. Notably, LATS achieves state-of-the-art pass@1 accuracy (92.7%) for programming on HumanEval with GPT-4 and demonstrates gradient-free performance (average score of 75.9) comparable to gradient-based fine-tuning for web navigation on WebShop with GPT-3.5. Code can be found at https://github.com/lapisrocks/LanguageAgentTreeSearch

cs.AI↗

arXiv2023

A Sentence Speaks a Thousand Images: Domain Generalization through Distilling CLIP with Language Guidance

Domain generalization studies the problem of training a model with samples from several domains (or distributions) and then testing the model with samples from a new, unseen domain. In this paper, we propose a novel approach for domain generalization that leverages recent advances in large vision-language models, specifically a CLIP teacher model, to train a smaller model that generalizes to unseen domains. The key technical contribution is a new type of regularization that requires the student's learned image representations to be close to the teacher's learned text representations obtained from encoding the corresponding text descriptions of images. We introduce two designs of the loss function, absolute and relative distance, which provide specific guidance on how the training process of the student model should be regularized. We evaluate our proposed method, dubbed RISE (Regularized Invariance with Semantic Embeddings), on various benchmark datasets and show that it outperforms several state-of-the-art domain generalization methods. To our knowledge, our work is the first to leverage knowledge distillation using a large vision-language model for domain generalization. By incorporating text-based information, RISE improves the generalization capability of machine learning models.

cs.CV↗