collaborators

7 papers

cs.AI2026

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…

cs.CL2025

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…

cs.CL2025

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…

cs.CL2025

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…

cs.CL2025

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…

cs.CR2025

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…