mlsanityData to 7 Oct 2026

A Survey of Black-Box Adversarial Attacks on Computer Vision Models

arXiv 1912.01667 ↗First posted 3 Dec 2019cs.LG cs.CR cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life scenarios, pose a severe challenge to their applicability, pushing research into the direction which aims to enhance the robustness of these models. After the introduction of these perturbations by Szegedy et al. [1], significant amount of research has focused on the reliability of such models, primarily in two aspects - white-box, where the adversary has access to the targeted model and related parameters; and the black-box, which resembles a real-life scenario with the adversary having almost no knowledge of the model to be attacked. To provide a comprehensive security cover, it is essential to identify, study, and build defenses against such attacks. Hence, in this paper, we propose to present a comprehensive comparative study of various black-box adversarial attacks and defense techniques.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 8; 2023: 5; 2024: 9; 2025: 5; 2026: 1.

36 papers.

Sort:

By area:

  1. 2021Trustworthy AI: From Principles to Practicescited by 206
  2. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 123
  3. 2023Interpretability Benchmark for Evaluating Spatial Misalignment of Prototypical Parts Explanationscited by 27
  4. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  5. 2022Pixle: a fast and effective black-box attack based on rearranging pixelscited by 20
  6. 2021On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attackscited by 17
  7. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  8. 2021Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attackscited by 16
  9. 2023Understanding and Improving Ensemble Adversarial Defensecited by 14
  10. 2021Black-box adversarial attacks using Evolution Strategiescited by 11
  11. 2021Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attackscited by 6
  12. 2023SoK: Pitfalls in Evaluating Black-Box Attackscited by 6
24 more
  1. 2023Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidencecited by 5
  2. 2024Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learningcited by 4
  3. 2025Adversarial Attacks against Neural Ranking Models via In-Context Learningcited by 4
  4. 2021Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimizationcited by 3
  5. 2022RES-HD: Resilient Intelligent Fault Diagnosis Against Adversarial Attacks Using Hyper-Dimensional Computingcited by 3
  6. 2024Exploring the Adversarial Frontier: Quantifying Robustness via Adversarial Hypervolumecited by 3
  7. 2021Saliency Diversified Deep Ensemble for Robustness to Adversariescited by 2
  8. 2024Enhancing TinyML Security: Study of Adversarial Attack Transferabilitycited by 2
  9. 2024Edge-Only Universal Adversarial Attacks in Distributed Learningcited by 2
  10. 2025False Alarms, Real Damage: Adversarial Attacks Using LLM-based Models on Text-based Cyber Threat Intelligence Systemscited by 2
  11. 2022Red Teaming with Mind Reading: White-Box Adversarial Policies Against RL Agentscited by 1
  12. 2022Physics-Guided Adversarial Machine Learning for Aircraft Systems Simulationcited by 1
  13. 2024Transparency Attacks: How Imperceptible Image Layers Can Fool AI Perceptioncited by 1
  14. 2025Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategiescited by 1
  15. 2021Distributionally Robust Multi-Output Regression Rankingcited by 0
  16. 2022Evaluation of Four Black-box Adversarial Attacks and Some Query-efficient Improvement Analysiscited by 0
  17. 2022Distributed Black-box Attack: Do Not Overestimate Black-box Attackscited by 0
  18. 2023General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothingcited by 0
  19. 2024TA3: Testing Against Adversarial Attacks on Machine Learning Modelscited by 0
  20. 2024Deep Model Merging: The Sister of Neural Network Interpretability -- A Surveycited by 0
  21. 2024PEAS: A Strategy for Crafting Transferable Adversarial Examplescited by 0
  22. 2025With Great Backbones Comes Great Adversarial Transferabilitycited by 0
  23. 2025Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attackscited by 0
  24. 2026A Unified Perspective on Adversarial Membership Manipulation in Vision Modelscited by 0