paper-with-me

홈 › Papers

Contrastive Self-Supervised Learning Leads to Higher Adversarial Susceptibility

2022-07-22 · Rohit Gupta, Naveed Akhtar, Ajmal Mian, Mubarak Shah

Contrastive self-supervised learning (CSL) has managed to match or surpass the performance of supervised learning in image and video classification. However, it is still largely unknown if the nature of the representations induced by the two learning paradigms is similar. We investigate this under the lens of adversarial robustness. Our analysis of the problem reveals that CSL has intrinsically higher sensitivity to perturbations over supervised learning. We identify the uniform distribution of data representation over a unit hypersphere in the CSL representation space as the key contributor to this phenomenon. We establish that this is a result of the presence of false negative pairs in the training process, which increases model sensitivity to input perturbations. Our finding is supported by extensive experiments for image and video classification using adversarial perturbations and other input corruptions. We devise a strategy to detect and remove false negative pairs that is simple, yet effective in improving model robustness with CSL training. We close up to 68% of the robustness gap between CSL and its supervised counterpart. Finally, we contribute to adversarial learning by incorporating our method in CSL. We demonstrate an average gain of about 5% over two different state-of-the-art methods in this domain.

📄 PDF Abstract BibTeX arXiv:2207.10862

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessSelf-Supervised LearningSensitivityVideo Classification

Methods 이 논문이 사용한 방법론

CSL Circular Smooth Label (CSL) is a classification-based rotation detection technique for arbitrary-oriented object detection. It is used for circularly distributed angle…

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

Adversarial Self-Supervised Contrastive Learning

2020-06-13 · NeurIPS 2020 12 · Minseon Kim, Jihoon Tack, Sung Ju Hwang

Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions, which are then used to augment the training of the model for improved robustness. While…

Adversarial AttackContrastive LearningSelf-Supervised LearningTransfer Learning

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning

2022-10-04 · NeurIPS 2023 11 · Charles Guille-Escuret, Pau Rodriguez, David Vazquez, Ioannis Mitliagkas 외

Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrastive learning to the simultaneous detecti…

Anomaly DetectionContrastive LearningOut-of-Distribution Detection

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

PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack

2022-09-14 · Junxuan Huang, Yatong An, Lu Cheng, Bai Chen 외

Despite recent success of self-supervised based contrastive learning model for 3D point clouds representation, the adversarial robustness of such pre-trained models raised concerns. Adversarial contrastive learning (ACL)…

3D ClassificationAdversarial AttackAdversarial RobustnessContrastive Learning