mlsanityData to 7 Oct 2026

Adversarial Attacks and Defenses in Images, Graphs and Text: A Review

arXiv 1909.08072 ↗First posted 17 Sep 2019cs.LG cs.CR stat.MLcited by 234

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNN) have achieved unprecedented success in numerous machine learning tasks in various domains. However, the existence of adversarial examples has raised concerns about applying deep learning to safety-critical applications. As a result, we have witnessed increasing interests in studying attack and defense mechanisms for DNN models on different data types, such as images, graphs and text. Thus, it is necessary to provide a systematic and comprehensive overview of the main threats of attacks and the success of corresponding countermeasures. In this survey, we review the state of the art algorithms for generating adversarial examples and the countermeasures against adversarial examples, for the three popular data types, i.e., images, graphs and text.

Key facts. Cited by 234 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 62; 2022: 52; 2023: 52; 2024: 36; 2025: 26; 2026: 6.

234 papers.

Sort:

By area:

  1. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  2. 2022Red Teaming Language Models with Language Modelscited by 983
  3. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  4. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 203
  5. 2023Defending Against Alignment-Breaking Attacks via Robustly Aligned LLMcited by 173
  6. 2021Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfercited by 147
  7. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  8. 2021Trustworthy AI: A Computational Perspectivecited by 93
  9. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  10. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  11. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 76
  12. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
38 more
  1. 2023BlackVIP: Black-Box Visual Prompting for Robust Transfer Learningcited by 70
  2. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  3. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  4. 2021Certified Robustness to Text Adversarial Attacks by Randomized [MASK]cited by 57
  5. 2022MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statisticcited by 53
  6. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 51
  7. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  8. 2021How Framelets Enhance Graph Neural Networkscited by 46
  9. 2021Single Node Injection Attack against Graph Neural Networkscited by 45
  10. 2021Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attackscited by 44
  11. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  12. 2021Reveal of Vision Transformers Robustness against Adversarial Attackscited by 43
  13. 2022Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networkscited by 39
  14. 2021The Dangers of Underclaiming: Reasons for Caution When Reporting How NLP Systems Failcited by 38
  15. 2021Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustnesscited by 35
  16. 2023MathAttack: Attacking Large Language Models Towards Math Solving Abilitycited by 31
  17. 2021On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learningcited by 29
  18. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  19. 2022Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarioscited by 29
  20. 2022Synthetic Data in Human Analysis: A Surveycited by 28
  21. 2022Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Modelscited by 28
  22. 2022Repairing Neural Networks by Leaving the Right Past Behindcited by 27
  23. 2022Adversarial Robustness of Neural-Statistical Features in Detection of Generative Transformerscited by 25
  24. 2021Adversarial Attacks on Deep Models for Financial Transaction Recordscited by 24
  25. 2022Universal Adversarial Examples in Remote Sensing: Methodology and Benchmarkcited by 24
  26. 2021Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attackcited by 23
  27. 2021ML Attack Models: Adversarial Attacks and Data Poisoning Attackscited by 23
  28. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
  29. 2022TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimizationcited by 21
  30. 2023Towards Viewpoint-Invariant Visual Recognition via Adversarial Trainingcited by 19
  31. 2021Jointly Attacking Graph Neural Network and its Explanationscited by 18
  32. 2023Continual Graph Learning: A Surveycited by 17
  33. 2021Detecting Adversarial Examples by Input Transformations, Defense Perturbations, and Votingcited by 16
  34. 2021Deep neural network enabled corrective source term approach to hybrid analysis and modelingcited by 16
  35. 2021Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methodscited by 16
  36. 2022A Perturbation-Constrained Adversarial Attack for Evaluating the Robustness of Optical Flowcited by 16
  37. 2023Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networkscited by 16
  38. 2023Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debiascited by 16

50 most cited of 234 All 234 (JSON)