Hui Xue

ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing

2023

Recent studies have shown that higher accuracy on ImageNet usually leads to better robustness against different corruptions. Therefore, in this paper, instead of following the traditional research paradigm that investigates new out-of-distribution corruptions or perturbations …

KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration

2025

Zero-shot anomaly detection (ZSAD) identifies anomalies without needing training samples from the target dataset, essential for scenarios with privacy concerns or limited data. Vision-language models like CLIP show potential in ZSAD but have limitations: relying …

Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models

2025 · arXiv (Cornell University)

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and accuracy. While learning-based methods trained …