TenAd: A Tensor-based Low-rank Black Box Adversarial Attack for Video Classification
This work addresses the vulnerability of deep learning models in video classification to adversarial attacks, particularly in black-box settings, offering a more efficient and effective solution for security testing.
The paper tackled the problem of black-box adversarial attacks on video classification models by proposing TenAd, a tensor-based low-rank method that leverages the multi-dimensional structure of video data, resulting in higher attack success rates and improved query efficiency compared to state-of-the-art methods.
Deep learning models have achieved remarkable success in computer vision but remain vulnerable to adversarial attacks, particularly in black-box settings where model details are unknown. Existing adversarial attack methods(even those works with key frames) often treat video data as simple vectors, ignoring their inherent multi-dimensional structure, and require a large number of queries, making them inefficient and detectable. In this paper, we propose \textbf{TenAd}, a novel tensor-based low-rank adversarial attack that leverages the multi-dimensional properties of video data by representing videos as fourth-order tensors. By exploiting low-rank attack, our method significantly reduces the search space and the number of queries needed to generate adversarial examples in black-box settings. Experimental results on standard video classification datasets demonstrate that \textbf{TenAd} effectively generates imperceptible adversarial perturbations while achieving higher attack success rates and query efficiency compared to state-of-the-art methods. Our approach outperforms existing black-box adversarial attacks in terms of success rate, query efficiency, and perturbation imperceptibility, highlighting the potential of tensor-based methods for adversarial attacks on video models.