Adversarial Self-Supervised Contrastive Learning

By Minseon Kim, Jihoon Tack, Sung Ju Hwang. 2020

286 citations recorded by the source corpus.

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 some recent works propose semi-supervised adversarial learning methods that utilize unlabeled data, they still require class labels. However, do we really need class labels at all, for adversarially robust training of deep neural networks? In this paper, we propose a novel adversarial attack for unlabeled data, which makes the model confuse the instance-level identities of the perturbed data samples. Further, we present a self-supervised contrastive learning framework to adversarially train a robust neural network without labeled data, which aims to maximize the similarity between a random augmentation of a data sample and its instance-wise adversarial perturbation. We validate our method, Robust Contrastive Learning (RoCL), on multiple benchmark datasets, on which it obtains comparable robust accuracy over state-of-the-art supervised adversarial learning methods, and significantly improved robustness against the black box and unseen types of attacks. Moreover, with further joint fine-tuning with supervised adversarial loss, RoCL obtains even higher robust accuracy over using self-supervised learning alone. Notably, RoCL also demonstrate impressive results in robust transfer learning.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hongzhi Yin
2. Tong Chen
3. Junliang Yu
4. Xin Xia
5. Elisa Ricci
6. Yonglong Tian
7. Zi-Liang Huang
8. Jinwoo Shin

Citations in the corpus

• Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation (2022, methodology): “This training scheme has been successfully employed in different fields such as image and video classification [25], [53], [54], as well as natural language processing [55], [56] and audio representation learning [57], [58], [59].”
• Self-Supervised Learning for Recommender Systems: A Survey (2022, background): “To prevent the mode collapse problem in two-encoder-based co-training [129], it imposes a divergence constraint on the two encoders to keep them slightly different by exploiting adversarial examples [138].”
• A Survey on Self-Supervised Learning: Algorithms, Applications, and Future Trends (2023, unknown): “…[145], multi-task learning [157], [158], transfer learning [159], [160], [161], graph NNs [147], [162], [163], reinforcement learning [164], [165], [166], few-shot learning [167], [168], neural architecture search [169], robust learning [146], [170], [171], [172], and meta-learning [173], [174].”
• ADBench: Anomaly Detection Benchmark (2022, background): “Model robustness has been an important aspect of anomaly detection and adversarial machine learning [24, 41, 47, 76, 177].”
• CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances (2020, background): “, uncertainty or robustness) are rarely investigated [25, 31].”
• Recent Advances in Adversarial Training for Adversarial Robustness (2021, background): “, 2020] where a distributionbased min-max problem is derived from a general view; bilateral adversarial training [Wang and Zhang, 2019] where the model is training on both perturbed images and labels; adversarial training based on feature scatter [Zhang and Wang, 2019], which utilizes a distance met”
• Divide and Contrast: Self-supervised Learning from Uncurated Data (2021, background): “Finally, contrastive learning has also been applied to supervised image classification [48], image translation [70], knowledge distillation [89, 77], and adversarial learning [49].”
• Hard Negative Mixing for Contrastive Learning (2020, background): “In RoCL [23], the authors question the need for class labels for adversarially robust training, and present a self-supervised contrastive learning framework that significantly improved robustness.”