22 citations · 37 across the 16 of their papers we have counts for
16 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…
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…
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…
TruthFlow: Truthful LLM Generation via Representation Flow Correction
Hanyu Wang, Bochuan Cao, Yuanpu Cao +1
Large language models (LLMs) are known to struggle with consistently generating truthful responses. While various representation intervention techniques have been proposed, these m…
Data Free Backdoor Attacks
Bochuan Cao, Jinyuan Jia, Chuxuan Hu +5
Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing ba…
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…
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
Yuanpu Cao, Tianrong Zhang, Bochuan Cao +4
Researchers have been studying approaches to steer the behavior of Large Language Models (LLMs) and build personalized LLMs tailored for various applications. While fine-tuning see…
Watch the Watcher! Backdoor Attacks on Security-Enhancing Diffusion Models
Changjiang Li, Ren Pang, Bochuan Cao +4
Thanks to their remarkable denoising capabilities, diffusion models are increasingly being employed as defensive tools to reinforce the security of other models, notably in purifyi…
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response
Tianrong Zhang, Bochuan Cao, Yuanpu Cao +3
The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mountin…
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…
On the Difficulty of Defending Contrastive Learning against Backdoor Attacks
Changjiang Li, Ren Pang, Bochuan Cao +4
Recent studies have shown that contrastive learning, like supervised learning, is highly vulnerable to backdoor attacks wherein malicious functions are injected into target models,…
Stealthy and Persistent Unalignment on Large Language Models via Backdoor Injections
Yuanpu Cao, Bochuan Cao, Jinghui Chen
Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concen…
IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI
Bochuan Cao, Changjiang Li, Ting Wang +3
Diffusion-based image generation models, such as Stable Diffusion or DALL-E 2, are able to learn from given images and generate high-quality samples following the guidance from pro…
On the Safety of Open-Sourced Large Language Models: Does Alignment Really Prevent Them From Being Misused?
Hangfan Zhang, Zhimeng Guo, Huaisheng Zhu +5
Large Language Models (LLMs) have achieved unprecedented performance in Natural Language Generation (NLG) tasks. However, many existing studies have shown that they could be misuse…
Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time
Huaxiu Yao, Caroline Choi, Bochuan Cao +3
Distribution shift occurs when the test distribution differs from the training distribution, and it can considerably degrade performance of machine learning models deployed in the…