17 citations · 58 across the 25 of their papers we have counts for
29 papers
Discovery or Memorization? A Faithful Benchmark for Real-World Business-Logic Vulnerability Discovery
Rui Yang, Yichao Xu, Zhuohao Zhang +4
The rapid advancement of cybersecurity agents in vulnerability discovery has increased the need for benchmarks that evaluate their capabilities accurately. However, synthetic bench…
HarnessTTT: Learn to Optimize Harness at Test-Time for Scientific Discovery
Yingzi Ma, Yulong Cao, Nanxi Li +5
Scientific discovery with language models requires finding the best valid solution within a finite computational budget. We study how feedback from this search can improve the proc…
Red-TTT: Test-Time Training for Automated Jailbreaking Large Language Models
Tongyan Hu, Hao Li, Xiaogeng Liu +8
Large language models remain vulnerable to jailbreaks, and automated red teaming is the standard way to find jailbreaks in large language models at scale. Current methods either dr…
EvoSafeHarness: Evolving Model- and Domain-Specific Harnesses for Securing Agents
Nanxi Li, Yingzi Ma, Yulong Cao +7
Large language model (LLM) agents can translate natural-language requests into real-world actions, creating safety risks from both indirect prompt injections and directly harmful r…
KeyPooling: Measuring Where LLM API Relay Paths Collapse Prompt Cache Isolation
Bowen Sun, Yixi Cai, Xiaogeng Liu +3
Large language model (LLM) API relays authenticate customers separately but often forward requests through shared provider credentials. Providers scope prompt caches to upstream pr…
Decomposition Attacks Across Unlinkable Identities: Limits of Stateful Defenses for LLM Services
Bowen Sun, Zhengyue Zhao, Xiaogeng Liu +2
Most large language model services use stateless defenses, which judge only the current request, to refuse harmful tasks. Decomposition attacks exploit this limitation by splitting…
When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
Yechao Zhang, Shiqian Zhao, Jiawen Zhang +5
Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and proactive background execution. Thi…
MaskForge: Structure-Aware Adaptive Attacks for Jailbreaking Diffusion Large Language Models
Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu +3
Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autor…
When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
Xiaogeng Liu, Xinyan Wang, Yingzi Ma +2
On-policy self-distillation (OPSD) trains a student on its own rollouts using a privileged teacher, but its standard objective weights all generated tokens equally, implicitly trea…
LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails
Nanxi Li, Zhengyue Zhao, Chaowei Xiao
Guardrails are a critical safety layer for modern AI systems, but their operating regime is changing. As LLMs are deployed as customized assistants, safety policies are increasingl…
DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents
Zhaorun Chen, Xun Liu, Haibo Tong +14
AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and fl…
ROM: Real-time Overthinking Mitigation via Streaming Detection and Intervention
Xinyan Wang, Xiaogeng Liu, Ming Pei +1
Large Reasoning Models (LRMs) often reach a correct solution before their long Chain-of-Thought trace ends, yet continue with redundant verification, repeated attempts, or unnecess…
AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling
Xiaogeng Liu, Chaowei Xiao
Recent advancements in jailbreaking large language models (LLMs), such as AutoDAN-Turbo, have demonstrated the power of automated strategy discovery. AutoDAN-Turbo employs a lifelo…
Your Harness is Not Secure: Benchmarking Real-world Threat of Command Line Interface Agent
Weidi Luo, Qiming Zhang, Tianyu Lu +9
Command-line interface (CLI) agents powered by large language models (LLMs) can interpret natural-language requests, plan multi-step tasks, execute shell commands, and modify files…
MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
Yaolun Zhang, Xiaogeng Liu, Chaowei Xiao
Large Language Models (LLMs) have demonstrated the ability to solve a wide range of practical tasks within multi-agent systems. However, existing human-designed multi-agent framewo…
DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
Hao Li, Xiaogeng Liu, Hung-Chun Chiu +3
Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities. By interacting with external environments through…
OET: Optimization-based prompt injection Evaluation Toolkit
Jinsheng Pan, Xiaogeng Liu, Chaowei Xiao
Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation, enabling their widespread adoption across various domains.…
Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
Weidi Luo, Tianyu Lu, Qiming Zhang +8
Recent advances in multi-modal large reasoning models (MLRMs) have shown significant ability to interpret complex visual content. While these models enable impressive reasoning cap…
RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process
Peiran Wang, Xiaogeng Liu, Chaowei Xiao
In this study, we introduce RePD, an innovative attack Retrieval-based Prompt Decomposition framework designed to mitigate the risk of jailbreak attacks on large language models (L…
System-Level Defense against Indirect Prompt Injection Attacks: An Information Flow Control Perspective
Fangzhou Wu, Ethan Cecchetti, Chaowei Xiao
Large Language Model-based systems (LLM systems) are information and query processing systems that use LLMs to plan operations from natural-language prompts and feed the output of…
InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models
Hao Li, Xiaogeng Liu
Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer…
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
Xiaogeng Liu, Peiran Li, Edward Suh +7
In this paper, we propose AutoDAN-Turbo, a black-box jailbreak method that can automatically discover as many jailbreak strategies as possible from scratch, without any human inter…
JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
Weidi Luo, Siyuan Ma, Xiaogeng Liu +2
With the rapid advancements in Multimodal Large Language Models (MLLMs), securing these models against malicious inputs while aligning them with human values has emerged as a criti…
Automatic and Universal Prompt Injection Attacks against Large Language Models
Xiaogeng Liu, Zhiyuan Yu, Yizhe Zhang +2
Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions. However, their capabilities can be ex…