16 papers
ElasticBack: Stealthy Conditional Backdoor in LLM-Agent Skills via Coupled Trigger-Rule Optimization
Hao Sui, Simeng Qin, Jie Liao +3
Agent skills, bundles of instructions and resources that an LLM agent loads on demand, form an emerging supply chain where a single poisoned skill can persistently compromise every…
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
Xiaojun Jia, Jie Liao, Simeng Qin +5
Agent skills are emerging as an important attack surface in LLM-based systems. Through an empirical study of existing skill scanners, we find that current defenses primarily rely o…
PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
Lingzhi Yuan, Xinfeng Li, Chejian Xu +6
Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, pa…
Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search
Xun Huang, Simeng Qin, Xiaoshuang Jia +6
As Large Language Models (LLMs) are increasingly used, their security risks have drawn increasing attention. Existing research reveals that LLMs are highly susceptible to jailbreak…
Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignment
Ruoxi Cheng, Haoxuan Ma, Weixin Wang +7
Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with r…
ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference
Siyuan Ma, Bo Gao, Xiaojun Jia +6
The paradigm of large language model (LLM) reasoning is shifting from parameter scaling to test-time compute scaling, yet many existing approaches still rely on uniform brute-force…