12 papers
SkillGrad: Optimizing Agent Skills Like Gradient Descent
Hanyu Wang, Yifan Lan, Bochuan Cao +2
Agent skills provide a lightweight way to adapt LLM agents to specialized domains by storing reusable procedural knowledge in structured files. However, whether downloaded from thi…
You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
Bochuan Cao, Changjiang Li, Yuanpu Cao +3
Large language models (LLMs) have been widely adopted across various applications, leveraging customized system prompts for diverse tasks. Facing potential system prompt leakage ri…
JoPA:Explaining Large Language Model's Generation via Joint Prompt Attribution
Yurui Chang, Bochuan Cao, Yujia Wang +2
Large Language Models (LLMs) have demonstrated impressive performances in complex text generation tasks. However, the contribution of the input prompt to the generated content stil…
Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation
Yurui Chang, Bochuan Cao, Lu Lin
While large language models have demonstrated exceptional performance across a wide range of tasks, they remain susceptible to hallucinations -- generating plausible yet factually…
AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion models
Yaopei Zeng, Yuanpu Cao, Bochuan Cao +3
Recent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation o…
Your Agent Can Defend Itself against Backdoor Attacks
Li Changjiang, Liang Jiacheng, Cao Bochuan +2
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. Thes…