mlsanityData to 7 Oct 2026

Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization

arXiv 2305.00374 ↗First posted 30 Apr 2023cs.LG cs.CRcited by 10

Not on the map. Why?

Abstract (arXiv)

Adversarial contrastive learning (ACL) is a technique that enhances standard contrastive learning (SCL) by incorporating adversarial data to learn a robust representation that can withstand adversarial attacks and common corruptions without requiring costly annotations. To improve transferability, the existing work introduced the standard invariant regularization (SIR) to impose style-independence property to SCL, which can exempt the impact of nuisance style factors in the standard representation. However, it is unclear how the style-independence property benefits ACL-learned robust representations. In this paper, we leverage the technique of causal reasoning to interpret the ACL and propose adversarial invariant regularization (AIR) to enforce independence from style factors. We regulate the ACL using both SIR and AIR to output the robust representation. Theoretically, we show that AIR implicitly encourages the representational distance between different views of natural data and their adversarial variants to be independent of style factors. Empirically, our experimental results show that invariant regularization significantly improves the performance of state-of-the-art ACL methods in terms of both standard generalization and robustness on downstream tasks. To the best of our knowledge, we are the first to apply causal reasoning to interpret ACL and develop AIR for enhancing ACL-learned robust representations. Our source code is at https://github.com/GodXuxilie/Enhancing_ACL_via_AIR.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 43 of its 66 references that are in the map. First posted on arXiv 30 Apr 2023.

Builds on

43 of 66 references.

References · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  9. 2016Wide Residual Networkscited by 3,057
  10. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  11. 2019Invariant Risk Minimizationcited by 1,832
  12. 2016Adversarial examples in the physical worldcited by 1,762
31 more
  1. 2021An Empirical Study of Training Self-Supervised Vision Transformerscited by 1,610
  2. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  3. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  4. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  5. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 722
  6. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  7. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  8. 2020Contrastive Learning with Hard Negative Samplescited by 619
  9. 2021ImageNet-21K Pretraining for the Massescited by 607
  10. 2020Keystroke Dynamics as Part of Lifeloggingcited by 334
  11. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  12. 2019Adversarial Examples Improve Image Recognitioncited by 283
  13. 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
  14. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  15. 2020Representation Learning via Invariant Causal Mechanismscited by 197
  16. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  17. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  18. 2020Adversarial Self-Supervised Contrastive Learningcited by 138
  19. 2018Invariance, Causality and Robustnesscited by 123
  20. 2021Counterfactual Generative Networkscited by 111
  21. 2020Contrastive Learning with Adversarial Examplescited by 91
  22. 2021When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?cited by 76
  23. 2014Visual Causal Feature Learningcited by 59
  24. 2020A Causal View on Robustness of Neural Networkscited by 53
  25. 2020What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentationcited by 50
  26. 2022Out-of-distribution Generalization with Causal Invariant Transformationscited by 45
  27. 2022Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustnesscited by 20
  28. 2023Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learningcited by 20
  29. 2023Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selectioncited by 14
  30. 2022Adversarial Contrastive Learning via Asymmetric InfoNCEcited by 13
  31. 2021Robustness through Data Augmentation Loss Consistencycited by 8

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 4; 2025: 4.

10 papers.

  1. 2024Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Modelscited by 119
  2. 2024Few-Shot Adversarial Prompt Learning on Vision-Language Modelscited by 39
  3. 2023AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Frameworkcited by 9
  4. 2025Few-Shot Adversarial Low-Rank Fine-Tuning of Vision-Language Modelscited by 9
  5. 2024AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuningcited by 7
  6. 2024Enhancing the Resilience of Graph Neural Networks to Topological Perturbations in Sparse Graphscited by 3
  7. 2025How does Labeling Error Impact Contrastive Learning? A Perspective from Data Dimensionality Reductioncited by 1
  8. 2023Generalization Bounds for Robust Contrastive Learning: From Theory to Practicecited by 0
  9. 2025Improving Adversarial Robustness via Phase and Amplitude-aware Promptingcited by 0
  10. 2025BIRD: Behavior Induction via Representation-structure Distillationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Exploring Transferability of Multimodal Adversarial Samples for Vision-Language Pre-training Models with Contrastive Learning
  2. 2025CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
  3. 2024Aligning Visual Contrastive learning models via Preference Optimization
  4. 2024One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
  5. 2026What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models
  6. 2026Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias Correction
  7. 2025AdversariaL attacK sAfety aLIgnment(ALKALI): Safeguarding LLMs through GRACE: Geometric Representation-Aware Contrastive Enhancement- Introducing Adversarial Vulnerability Quality Index (AVQI)
  8. 2024Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training