paper-with-me

홈 › Papers

Metric Learning for Adversarial Robustness

2019-09-03 · NeurIPS 2019 12 · Chengzhi Mao, Ziyuan Zhong, Junfeng Yang, Carl Vondrick, Baishakhi Ray

Deep networks are well-known to be fragile to adversarial attacks. We conduct an empirical analysis of deep representations under the state-of-the-art attack method called PGD, and find that the attack causes the internal representation to shift closer to the "false" class. Motivated by this observation, we propose to regularize the representation space under attack with metric learning to produce more robust classifiers. By carefully sampling examples for metric learning, our learned representation not only increases robustness, but also detects previously unseen adversarial samples. Quantitative experiments show improvement of robustness accuracy by up to 4% and detection efficiency by up to 6% according to Area Under Curve score over prior work. The code of our work is available at https://github.com/columbia/Metric_Learning_Adversarial_Robustness.

📄 PDF Abstract BibTeX arXiv:1909.00900

Code (1)

columbia/Metric_Learning_Adversarial_Robustness 공식 구현 tf

Tasks

Adversarial RobustnessMetric Learning

Similar Papers 제목 키워드 기반

A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks

2023-10-10 · Yang Wang, Bo Dong, Ke Xu, Haiyin Piao 외

Deep Neural Networks (DNNs) are widely used for computer vision tasks. However, it has been shown that deep models are vulnerable to adversarial attacks, i.e., their performances drop when imperceptible perturbations are…

Adversarial Robustness

Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attacks

2023-10-10 · Anastasia Antsiferova, Khaled Abud, Aleksandr Gushchin, Ekaterina Shumitskaya 외

Nowadays, neural-network-based image- and video-quality metrics perform better than traditional methods. However, they also became more vulnerable to adversarial attacks that increase metrics' scores without improving vi…

Adversarial Robustness

Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolume

2024-03-08 · Ping Guo, Cheng Gong, Xi Lin, Zhiyuan Yang 외

The escalating threat of adversarial attacks on deep learning models, particularly in security-critical fields, has underscored the need for robust deep learning systems. Conventional robustness evaluations have relied o…

Adversarial RobustnessBenchmarkingDeep Learning

To be Robust and to be Fair: Aligning Fairness with Robustness

2023-03-31 · Junyi Chai, Xiaoqian Wang

Adversarial training has been shown to be reliable in improving robustness against adversarial samples. However, the problem of adversarial training in terms of fairness has not yet been properly studied, and the relatio…

Adversarial AttackFairness

On Evaluating Adversarial Robustness of Volumetric Medical Segmentation Models

2024-06-12 · Hashmat Shadab Malik, Numan Saeed, Asif Hanif, Muzammal Naseer 외

Volumetric medical segmentation models have achieved significant success on organ and tumor-based segmentation tasks in recent years. However, their vulnerability to adversarial attacks remains largely unexplored, raisin…

Adversarial RobustnessMambaSegmentation