paper-with-me

홈 › Papers

Overparametrization improves robustness against adversarial attacks: A replication study

2022-02-20 · Ali Borji

Overparametrization has become a de facto standard in machine learning. Despite numerous efforts, our understanding of how and where overparametrization helps model accuracy and robustness is still limited. To this end, here we conduct an empirical investigation to systemically study and replicate previous findings in this area, in particular the study by Madry et al. Together with this study, our findings support the "universal law of robustness" recently proposed by Bubeck et al. We argue that while critical for robust perception, overparametrization may not be enough to achieve full robustness and smarter architectures e.g. the ones implemented by the human visual cortex) seem inevitable.

📄 PDF Abstract BibTeX arXiv:2202.09735

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based Attacks

2021-07-15 · Findings (NAACL) 2022 7 · Zhao Meng, Yihan Dong, Mrinmaya Sachan, Roger Wattenhofer

In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning…

Adversarial AttackContrastive LearningLanguage Modelling

Self-Supervised Contrastive Learning with Adversarial Perturbations for Robust Pretrained Language Models

2021-11-16 · ACL ARR November 2021 11 · Anonymous

In this paper, we present an approach to improve the robustness of BERT language models against word substitution-based adversarial attacks by leveraging adversarial perturbations for self-supervised contrastive learning…

Adversarial AttackContrastive Learning

Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks

2020-09-05 · NeurIPS 2020 12 · Wei-An Lin, Chun Pong Lau, Alexander Levine, Rama Chellappa 외

Adversarial training is a popular defense strategy against attack threat models with bounded Lp norms. However, it often degrades the model performance on normal images and the defense does not generalize well to novel a…

Adversarial Robustness

The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression

2022-01-13 · Hamed Hassani, Adel Javanmard

Successful deep learning models often involve training neural network architectures that contain more parameters than the number of training samples. Such overparametrized models have been extensively studied in recent y…

regression

Towards Out-of-Distribution Adversarial Robustness

2022-10-06 · Adam Ibrahim, Charles Guille-Escuret, Ioannis Mitliagkas, Irina Rish 외

Adversarial robustness continues to be a major challenge for deep learning. A core issue is that robustness to one type of attack often fails to transfer to other attacks. While prior work establishes a theoretical trade…

Adversarial Robustness