50 citations · 149 across the 15 of their papers we have counts for
8 papers · 1 filter
Diagnose Before You Refine: Multi-Dimensional Judge Feedback for Query-Efficient Jailbreak Attacks
Yixin Tan, Chia-Yi Hsu, Jiayang Liu +2
Automated jailbreak attacks rely on evaluation feedback to optimize adversarial prompts, but existing methods often lack fine-grained diagnostic information. We propose Jev-Guided…
DP-MIND: Differentially private memory-guided Long context Inference
Zhihao Liu, Yitian Cheng, Shuang Liu +3
LLM-as-a-Service has become a dominant paradigm for accessing large language models without requiring local deployment. However, the process raises severe privacy concerns when use…
Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance
Rui Wen, Jiayang Liu, Zeyu Yang +2
When a prompt injection attack succeeds, a Large Language Model (LLM) abandons its assigned system role to comply with an adversarial instruction. While prior work has extensively…
No Free Efficiency: Revisiting the Trade-off Between Training Efficiency and Model Vulnerability
Yiyong Liu, Jun Sakuma, Michael Backes +1
Training efficiency has become the central driver of recent progress in foundation models. To overcome the massive computational and data requirements of large-scale training, rese…
BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
Ziqing Yang, Rui Wen, Xinlei He +3
Prompt learning is a new machine learning paradigm that has attracted ample attention due to its simplicity and proven efficacy. Despite its growing adoption, the security vulnerab…
MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
Rui Wen, Mark Russinovich, Andrew Paverd +2
Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical appli…
Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills
Yiyong Liu, Chia-Yi Hsu, Chun-Ying Huang +3
LLM-powered coding agents increasingly make software supply chain decisions. They generate imports, recommend packages, and write installation commands. Prior work showed that thes…
SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability
Hanwei Zhang, Luo Cheng, Rui Wen +3
Explainable AI (XAI) is crucial for building transparent and trustworthy machine learning systems, especially in high-stakes domains. Concept Bottleneck Models (CBMs) have emerged…