1 citations · 1 across the 6 of their papers we have counts for
6 papers
Interpretable Multi-Hypersphere Deep Anomaly Detection for Open-set Supervised Anomaly Detection
Zhiji Yang, Fangyong Wang, Yue Li +2
Multi-class open-set anomaly detection requires a model to characterize the normal acceptance domain formed by multiple heterogeneous subdistributions using only class-labeled samp…
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…
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…
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…
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…
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…