7 papers
VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
Tri Cao, Bennett Lim, Yue Liu +7
Computer-Use Agents (CUAs) with full system access enable powerful task automation but pose significant security and privacy risks due to their ability to manipulate files, access…
LookAhead Tuning: Safer Language Models via Partial Answer Previews
Kangwei Liu, Mengru Wang, Yujie Luo +7
Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of m…
Automating Steering for Safe Multimodal Large Language Models
Lyucheng Wu, Mengru Wang, Ziwen Xu +4
Recent progress in Multimodal Large Language Models (MLLMs) has unlocked powerful cross-modal reasoning abilities, but also raised new safety concerns, particularly when faced with…
ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
Kangwei Liu, Siyuan Cheng, Bozhong Tian +7
Large language models (LLMs) have been increasingly applied to automated harmful content detection tasks, assisting moderators in identifying policy violations and improving the ov…
ReLearn: Unlearning via Learning for Large Language Models
Haoming Xu, Ningyuan Zhao, Liming Yang +7
Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent token…
PhishIntel: Toward Practical Deployment of Reference-Based Phishing Detection
Yuexin Li, Hiok Kuek Tan, Qiaoran Meng +6
Phishing is a critical cyber threat, exploiting deceptive tactics to compromise victims and cause significant financial losses. While reference-based phishing detectors (RBPDs) hav…