4 papers
Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery
Keyu Lin, Fei Ye, Qihe Liu +2
Continual learning (CL) enables models to acquire new knowledge from sequentially arriving tasks while retaining previously learned knowledge. However, in practical scenarios, task…
TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling
Ling Zhou, Yihao Huang, Jingling Sun +4
Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and image-based jailbreaks, video ja…
Towards a Novel Perspective on Adversarial Examples Driven by Frequency
Zhun Zhang, Yi Zeng, Qihe Liu +1
Enhancing our understanding of adversarial examples is crucial for the secure application of machine learning models in real-world scenarios. A prevalent method for analyzing adver…
Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks
Zhewei Wu, Ruilong Yu, Qihe Liu +3
Adversarial attacks in visual object tracking have significantly degraded the performance of advanced trackers by introducing imperceptible perturbations into images. However, ther…