collaborators

8 papers

cs.CR2026

AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing

Yuexin Li, Wenjie Qu, Linyu Wu +5

Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable…

cs.CR2026

WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections

Tri Cao, Yulin Chen, Hieu Cao +8

Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedd…

cs.LG2026

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation

Lilin Zhang, Yimo Guo, Yue Li +2

Deep neural networks are highly vulnerable to adversarial examples, i.e.,small perturbations that can significantly degrade model performance. While adversarial training has become…

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.CR2025

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition

Yulin Chen, Haoran Li, Yuexin Li +3

Large language models (LLMs) have shown remarkable performance across a range of NLP tasks. However, their strong instruction-following capabilities and inability to distinguish in…

cs.AI2025

Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?

Yufei He, Yuexin Li, Jiaying Wu +3

As large language models (LLMs) continue to evolve, ensuring their alignment with human goals and values remains a pressing challenge. A key concern is \textit{instrumental converg…