mlsanityData to 7 Oct 2026

Automated Discovery of Adaptive Attacks on Adversarial Defenses

arXiv 2102.11860 ↗First posted 23 Feb 2021cs.LG cs.CV stat.MLcited by 22

Not on the map. Why?

Abstract (arXiv)

Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense's inner workings or approaches based on an ensemble of fixed attacks, none of which may be effective for the specific defense at hand. Our key observation is that adaptive attacks are composed of reusable building blocks that can be formalized in a search space and used to automatically discover attacks for unknown defenses. We evaluated our approach on 24 adversarial defenses and show that it outperforms AutoAttack, the current state-of-the-art tool for reliable evaluation of adversarial defenses: our tool discovered significantly stronger attacks by producing 3.0%-50.8% additional adversarial examples for 10 models, while obtaining attacks with slightly stronger or similar strength for the remaining models.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 23 Feb 2021.

Builds on

36 of 51 references.

References · 36

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  7. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  10. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  11. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  12. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
24 more
  1. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  2. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  3. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  4. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  5. 2017Countering Adversarial Images using Input Transformationscited by 517
  6. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  7. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  8. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  9. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  10. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 275
  11. 2017On Detecting Adversarial Perturbationscited by 232
  12. 2015Non-stochastic Best Arm Identification and Hyperparameter Optimizationcited by 219
  13. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  14. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  15. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  16. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 86
  17. 2016Adversarial Examples Detection in Deep Networks with Convolutional Filter Statisticscited by 77
  18. 2015Adversarial Manipulation of Deep Representationscited by 56
  19. 2019Enhancing Adversarial Defense by k-Winners-Take-Allcited by 51
  20. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  21. 2020Composite Adversarial Attackscited by 29
  22. 2018ResNets Ensemble via the Feynman-Kac Formalism to Improve Natural and Robust Accuraciescited by 18
  23. 2018Defending Against Machine Learning Model Stealing Attacks Using Deceptive Perturbationscited by 11
  24. 2020HYDRA: Pruning Adversarially Robust Neural Networkscited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 5; 2024: 6; 2025: 2; 2026: 3.

22 papers.

Sort:

By area:

  1. 2023DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purificationcited by 36
  2. 2021Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examplescited by 23
  3. 2022Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attackscited by 18
  4. 2022A2: Efficient Automated Attacker for Boosting Adversarial Trainingcited by 10
  5. 2021Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attackscited by 7
  6. 2023Improving Fast Minimum-Norm Attacks with Hyperparameter Optimizationcited by 4
  7. 2024Towards Robust Vision Transformer via Masked Adaptive Ensemblecited by 4
  8. 2024Achieving Domain-Independent Certified Robustness via Knowledge Continuitycited by 3
  9. 2022Adversarial Attack and Defense for Non-Parametric Two-Sample Testscited by 2
  10. 2023RNN-Guard: Certified Robustness Against Multi-frame Attacks for Recurrent Neural Networkscited by 1
  11. 2025On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabelingcited by 1
  12. 2026Fortifying Time Series: DTW-Certified Robust Anomaly Detectioncited by 1
10 more
  1. 2022A Multi-objective Memetic Algorithm for Auto Adversarial Attack Optimization Designcited by 0
  2. 2023A Minimax Approach Against Multi-Armed Adversarial Attacks Detectioncited by 0
  3. 2023Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbationscited by 0
  4. 2024Redesigning Traffic Signs to Mitigate Machine-Learning Patch Attackscited by 0
  5. 2024Reinforced Compressive Neural Architecture Search for Versatile Adversarial Robustnesscited by 0
  6. 2024DataFreeShield: Defending Adversarial Attacks without Training Datacited by 0
  7. 2024HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attackscited by 0
  8. 2025SoK: Systematic analysis of adversarial threats against deep learning approaches for autonomous anomaly detection systems in SDN-IoT networkscited by 0
  9. 2026Dashed Line Defense: Plug-And-Play Defense Against Adaptive Score-Based Query Attackscited by 0
  10. 2026Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluationcited by 0