13 papers
SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment
Qinghua Mao, Wanying Qu, Dadi Guo +8
The performance of LLM-based agents is jointly shaped by the base model and the harness used when interacting with the environment. This exposes them to safety risks in both harmfu…
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
Wanying Qu, Qinghua Mao, Yu Li +12
The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime contro…
SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks
Siyuan Li, Aodu Wulianghai, Zehao Liu +8
Large Language Models (LLMs) are increasingly deployed in interactive settings, where user intent commonly unfolds through multi-turn dialogue. Multi-turn jailbreaks exploit this p…
Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks
Siyuan Li, Zehao Liu, Haoyu Li +5
As LLMs become increasingly integrated into complex applications, their vulnerability to adversarial attacks has raised significant concerns. However, existing defenses remain reac…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Dongrui Liu, Yu Li, Zhonghao Yang +47
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…
GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction
Jinze Gu, Qinghua Mao, Xi Lin +1
Retrieval-Augmented Generation (RAG) enhances LLMs by grounding generation in query-relevant external evidence. Beyond unstructured text corpora, Graph RAG integrates knowledge gra…
Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing
Qinghua Mao, Xi Lin, Jinze Gu +3
Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces critical safety risks: adversarie…
Lightweight Stylistic Consistency Profiling: Robust Detection of LLM-Generated Textual Content for Multimedia Moderation
Siyuan Li, Aodu Wulianghai, Xi Lin +6
The increasing prevalence of Large Language Models (LLMs) in content creation has made distinguishing human-written textual content from LLM-generated counterparts a critical task…
DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis
Siyuan Li, Aodu Wulianghai, Guangyan Li +5
The rapid advancement of large language models (LLMs) presents new security challenges, particularly in detecting machine-generated text used for misinformation, impersonation, and…
TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
Weian Mao, Xi Lin, Wei Huang +5
Extended reasoning in large language models (LLMs) creates severe KV cache memory bottlenecks. Leading KV cache compression methods estimate KV importance using attention scores fr…
CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
Siyuan Li, Zehao Liu, Xi Lin +6
As Large Language Models (LLMs) are increasingly deployed in complex applications, their vulnerability to adversarial attacks raises urgent safety concerns, especially those evolvi…
HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense
Siyuan Li, Xi Lin, Jun Wu +5
Jailbreak attacks pose significant threats to large language models (LLMs), enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep…
Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation
Zehao Liu, Xi Lin
Large Language Models (LLMs) have gained considerable popularity and protected by increasingly sophisticated safety mechanisms. However, jailbreak attacks continue to pose a critic…