17 citations · 21 across the 16 of their papers we have counts for
19 papers
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…
Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience
Zixuan Wang, Hao Li, Fengyu Gao +5
Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection a…
Skynet: Workflow-Level Anomaly Detection for Agentic AI via Semantic and Structural Modeling
Chaoyu Zhang, Hexuan Yu, Heng Jin +6
Agentic AI systems execute complex tasks through long-horizon workflows of planning, tool use, and multi-agent coordination. Task failures in these systems often originate from a s…
MechAudit-40: White-Box Auditing across 40 LLM Attack Mechanisms
Zhen Guo, Shanghao Shi, Shamim Yazdani +2
While LLM attacks span prompt optimization, multi-turn context manipulation, retrieval poisoning, and model backdoors, white-box defenses are typically evaluated on isolated attack…
ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection
Xinhang Ma, Chaowei Xiao, William Yeoh +2
Indirect prompt injection (IPI) plants instructions in the content a tool-using LLM agent reads, steering the agent into harmful tool calls. The strongest defenses are system-level…
Planning to Hammer: Difficulty-Aware Decomposition for Automating Rocq Proofs
Ning Zhang, Nongyu Di, Zenan Li +2
As AI-generated code proliferates, formal verification, particularly through interactive theorem provers such as Rocq and Isabelle, becomes increasingly important for ensuring soft…
AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents
Xinhang Ma, Taoran Li, Chaowei Xiao +3
Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work has proposed a variety of defensive approaches against IPI which can…
Think Twice Before You Act: Protecting LLM Agents Against Tool Description Poisoning via Isolated Planning
Shanghao Shi, Xiao Wang, Chaoyu Zhang +6
The integration of external tools has substantially expanded the capabilities of large language model (LLM) agents, but it also introduces new attack surfaces beyond prompt injecti…
From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning
Shanghao Shi, Chaoyu Zhang, Heng Jin +6
Federated learning (FL) enables multiple parties to collaboratively fine-tune language models for domain-specific tasks without sharing raw data. Since full model fine-tuning is of…
TokenPilot: Cache-Efficient Context Management for LLM Agents
Buqiang Xu, Zirui Xue, Dianmou Chen +12
As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize…
How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities
Ziwen Xu, Kewei Xu, Haoming Xu +8
Large Language Models (LLMs) are increasingly deployed in socially sensitive domains, yet their unpredictable behaviors, ranging from misaligned intent to inconsistent personality,…
TraceGuard: Process-Guided Firewall against Reasoning Backdoors in Large Language Models
Zhen Guo, Shanghao Shi, Hao Li +3
Large Reasoning Models (LRMs) introduce a reasoning-level attack surface: adversaries can corrupt intermediate inferences while preserving a plausible trace and an apparently benig…
AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management
Ruoyao Wen, Hao Li, Chaowei Xiao +1
Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working me…
AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
Hao Li, Ruoyao Wen, Shanghao Shi +3
AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes…
ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
Hao Li, Yankai Yang, G. Edward Suh +2
Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields. However, these systems are high…
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…
DarkMind: Latent Chain-of-Thought Backdoor in Customized LLMs
Zhen Guo, Shanghao Shi, Shamim Yazdani +2
With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents. However, their compl…
A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
Fangzhou Wu, Ning Zhang, Somesh Jha +2
Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and…
Exploring the Limits of ChatGPT in Software Security Applications
Fangzhou Wu, Qingzhao Zhang, Ati Priya Bajaj +4
Large language models (LLMs) have undergone rapid evolution and achieved remarkable results in recent times. OpenAI's ChatGPT, backed by GPT-3.5 or GPT-4, has gained instant popula…