2 papers
cs.CV2025
Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos
Songping Wang, Hanqing Liu, Yueming Lyu +5
Adversarial Training (AT) has been shown to significantly enhance adversarial robustness via a min-max optimization approach. However, its effectiveness in video recognition tasks…
cs.CV2023
Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videos
Wei Xingxing, Wang Songping, Yan Huanqian
Adversarial robustness assessment for video recognition models has raised concerns owing to their wide applications on safety-critical tasks. Compared with images, videos have much…