Selected work

Representative Papers

Pareto-Improving Adversarial Attacks with Primal-Dual Regularization

Oct 03, 2026

This study addresses the spurious trade-off between transferability and imperceptibility in adversarial attacks under a fixed perturbation budget. We propose ST, a plug-and-play primal-dual wrapper that performs two-step optimization updates grounded in Fenchel duality theory. By incorporating L∞ saturation regularization, ST transcends conventional perceptual priors and reveals the latent advantages of highly transferable attacks while enhancing stealthiness, all without requiring auxiliary models. Experimental results demonstrate that ST effectively expands the Pareto frontier, achieving synergistic optimization of transferability and imperceptibility. Specifically, it maintains or improves attack success rates while yielding 17% and 14% improvements in LPIPS and NIQE metrics, respectively.

0 citationsRead paper

TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning

Aug 12, 2026

This work proposes a text-driven unsupervised framework for video anomaly detection (VAD) that circumvents the reliance on scarce and heterogeneous annotated abnormal visual data. By leveraging temporal textual descriptions generated by large language models (LLMs) as surrogate training signals—without requiring any real anomalous videos—the method achieves cross-modal alignment between text and video through a frozen CLIP encoder. To capture both short- and long-term temporal dynamics, the approach introduces an event-evolution causal attention module that models the logical progression of events over time. Evaluated on the XD-Violence and UCF-Crime benchmarks, the proposed method significantly outperforms existing one-class and unsupervised VAD approaches, thereby eliminating the dependency on domain-specific abnormal visual examples.

0 citationsRead paper

Recent publications

Latest Papers

Pareto-Improving Adversarial Attacks with Primal-Dual Regularization

Oct 03, 2026

This study addresses the spurious trade-off between transferability and imperceptibility in adversarial attacks under a fixed perturbation budget. We propose ST, a plug-and-play primal-dual wrapper that performs two-step optimization updates grounded in Fenchel duality theory. By incorporating L∞ saturation regularization, ST transcends conventional perceptual priors and reveals the latent advantages of highly transferable attacks while enhancing stealthiness, all without requiring auxiliary models. Experimental results demonstrate that ST effectively expands the Pareto frontier, achieving synergistic optimization of transferability and imperceptibility. Specifically, it maintains or improves attack success rates while yielding 17% and 14% improvements in LPIPS and NIQE metrics, respectively.

0 citationsRead paper

TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning

Aug 12, 2026

This work proposes a text-driven unsupervised framework for video anomaly detection (VAD) that circumvents the reliance on scarce and heterogeneous annotated abnormal visual data. By leveraging temporal textual descriptions generated by large language models (LLMs) as surrogate training signals—without requiring any real anomalous videos—the method achieves cross-modal alignment between text and video through a frozen CLIP encoder. To capture both short- and long-term temporal dynamics, the approach introduces an event-evolution causal attention module that models the logical progression of events over time. Evaluated on the XD-Violence and UCF-Crime benchmarks, the proposed method significantly outperforms existing one-class and unsupervised VAD approaches, thereby eliminating the dependency on domain-specific abnormal visual examples.

0 citationsRead paper