mlsanityData to 7 Oct 2026

Combating Adversaries with Anti-Adversaries

arXiv 2103.14347 ↗First posted 26 Mar 2021cs.LG cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing the confidence of a network for the true class label, we propose the anti-adversary layer, aimed at countering this effect. In particular, our layer generates an input perturbation in the opposite direction of the adversarial one and feeds the classifier a perturbed version of the input. Our approach is training-free and theoretically supported. We verify the effectiveness of our approach by combining our layer with both nominally and robustly trained models and conduct large-scale experiments from black-box to adaptive attacks on CIFAR10, CIFAR100, and ImageNet. Our layer significantly enhances model robustness while coming at no cost on clean accuracy.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 35 of its 52 references that are in the map. First posted on arXiv 26 Mar 2021.

Builds on

35 of 52 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2018Neural Ordinary Differential Equationscited by 3,733
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  12. 2016Practical Black-Box Attacks against Machine Learningcited by 893
23 more
  1. 2018Robustness May Be at Odds with Accuracycited by 873
  2. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  3. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  4. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 588
  5. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  6. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  7. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  8. 2019On Evaluating Adversarial Robustnesscited by 442
  9. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  10. 2017Mitigating Adversarial Effects Through Randomizationcited by 382
  11. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  12. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  13. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  14. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  15. 2019Simple Black-box Adversarial Attackscited by 249
  16. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  17. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 158
  18. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  19. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
  20. 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 123
  21. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  22. 2018DARTS: Deceiving Autonomous Cars with Toxic Signscited by 53
  23. 2019Stochastic Three Points Method for Unconstrained Smooth Minimizationcited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 5; 2024: 4; 2025: 7; 2026: 5.

27 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  2. 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
  3. 2022Visual Prompting for Adversarial Robustnesscited by 33
  4. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 33
  5. 2025CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIPcited by 23
  6. 2023Defenses in Adversarial Machine Learning: A Surveycited by 14
  7. 2025AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defensescited by 14
  8. 2025Enhancing CLIP Robustness via Cross-Modality Alignmentcited by 14
  9. 2023Evaluation of Test-Time Adaptation Under Computational Time Constraintscited by 13
  10. 2024Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defencescited by 9
  11. 2023Robust Feature Inference: A Test-time Defense Strategy using Spectral Projectionscited by 3
  12. 2024Interpretability-Guided Test-Time Adversarial Defensecited by 3
15 more
  1. 2025Self-Calibrated Consistency can Fight Back for Adversarial Robustness in Vision-Language Modelscited by 3
  2. 2022Attacking Adversarial Defences by Smoothing the Loss Landscapecited by 2
  3. 2023Improving Adversarial Robustness of DEQs with Explicit Regulations Along the Neural Dynamicscited by 2
  4. 2026Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIPcited by 2
  5. 2022Unifying Gradients to Improve Real-world Robustness for Deep Networkscited by 1
  6. 2022Test-time adversarial detection and robustness for localizing humans using ultra wide band channel impulse responsescited by 1
  7. 2024Test-time Adversarial Defense with Opposite Adversarial Path and High Attack Time Costcited by 1
  8. 2025Adversarial Examples in Environment Perception for Automated Driving (Review)cited by 1
  9. 2025ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarkingcited by 1
  10. 2026A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Modelscited by 1
  11. 2026Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticitycited by 1
  12. 2026When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustnesscited by 1
  13. 2024DataCook: Crafting Anti-Adversarial Examples for Healthcare Data Copyright Protectioncited by 0
  14. 2025Diffusion or Non-Diffusion Adversarial Defenses: Rethinking the Relation between Classifier and Adversarial Purifiercited by 0
  15. 2026Closed-Loop Bidirectional Prompting for Adversarial Robustness of Vision Language Modelscited by 0