mlsanityData to 7 Oct 2026

ML Attack Models: Adversarial Attacks and Data Poisoning Attacks

arXiv 2112.02797 ↗First posted 6 Dec 2021cs.LG cs.CRcited by 23

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

Many state-of-the-art ML models have outperformed humans in various tasks such as image classification. With such outstanding performance, ML models are widely used today. However, the existence of adversarial attacks and data poisoning attacks really questions the robustness of ML models. For instance, Engstrom et al. demonstrated that state-of-the-art image classifiers could be easily fooled by a small rotation on an arbitrary image. As ML systems are being increasingly integrated into safety and security-sensitive applications, adversarial attacks and data poisoning attacks pose a considerable threat. This chapter focuses on the two broad and important areas of ML security: adversarial attacks and data poisoning attacks.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 43 of its 70 references that are in the map. First posted on arXiv 6 Dec 2021.

Builds on

43 of 70 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Active Learning Under Malicious Mislabeling and Poisoning Attacks1 Jan

Other references · 42

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Adversarial examples in the physical worldcited by 1,762
  8. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  9. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  11. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  12. 2018How To Backdoor Federated Learningcited by 745
30 more
  1. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  2. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  3. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  4. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  5. 2017Countering Adversarial Images using Input Transformationscited by 517
  6. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 500
  7. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  8. 2018Spectral Signatures in Backdoor Attackscited by 457
  9. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  10. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  11. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  12. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  13. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  14. 2017Detecting Adversarial Samples from Artifactscited by 244
  15. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  16. 2018AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networkscited by 137
  17. 2019Transferable Clean-Label Poisoning Attacks on Deep Neural Netscited by 129
  18. 2019Wasserstein Adversarial Examples via Projected Sinkhorn Iterationscited by 89
  19. 2017Exploring the Landscape of Spatial Robustnesscited by 81
  20. 2020Rethinking the Trigger of Backdoor Attackcited by 76
  21. 2019Bypassing Backdoor Detection Algorithms in Deep Learningcited by 69
  22. 2018Interpretable Adversarial Perturbation in Input Embedding Space for Textcited by 67
  23. 2020Bullseye Polytope: A Scalable Clean-Label Poisoning Attack with Improved Transferabilitycited by 65
  24. 2020Sparse-RS: a versatile framework for query-efficient sparse black-box adversarial attackscited by 65
  25. 2019Parsimonious Black-Box Adversarial Attacks via Efficient Combinatorial Optimizationcited by 49
  26. 2017Blocking Transferability of Adversarial Examples in Black-Box Learning Systemscited by 19
  27. 2020Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificatescited by 17
  28. 2020An Adversarial Attack Defending System for Securing In-Vehicle Networkscited by 8
  29. 2020An Empirical Study of Derivative-Free-Optimization Algorithms for Targeted Black-Box Attacks in Deep Neural Networkscited by 8
  30. 2020Towards adversarial robustness with 01 loss neural networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 7; 2025: 7; 2026: 2.

23 papers.

Sort:

By area:

  1. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  2. 2024Permute-and-Flip: An optimally stable and watermarkable decoder for LLMscited by 17
  3. 2023Efficient XAI Techniques: A Taxonomic Surveycited by 14
  4. 2025Algorithmic Collective Action with Two Collectivescited by 7
  5. 2023CALLOC: Curriculum Adversarial Learning for Secure and Robust Indoor Localizationcited by 5
  6. 2025Position: Bridge the Gaps between Machine Unlearning and AI Regulationcited by 5
  7. 2023Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attackscited by 4
  8. 2023Privacy Preservation in Artificial Intelligence and Extended Reality (AI-XR) Metaverses: A Surveycited by 3
  9. 2024The Effect of Data Poisoning on Counterfactual Explanationscited by 3
  10. 2024Adversarial Attacks and Defenses in Multivariate Time-Series Forecasting for Smart and Connected Infrastructurescited by 3
  11. 2022Defensive Distillation based Adversarial Attacks Mitigation Method for Channel Estimation using Deep Learning Models in Next-Generation Wireless Networkscited by 2
  12. 2025Adversarial Robustness of Deep Learning Models for Inland Water Body Segmentation from SAR Imagescited by 2
11 more
  1. 2023Improving Machine Learning Robustness via Adversarial Trainingcited by 1
  2. 2025Securing Traffic Sign Recognition Systems in Autonomous Vehiclescited by 1
  3. 2024Privacy and Security Implications of Cloud-Based AI Services : A Surveycited by 0
  4. 2024Mitigating Label Flipping Attacks in Malicious URL Detectors Using Ensemble Treescited by 0
  5. 2024Transfer-based Adversarial Poisoning Attacks for Online (MIMO-)Deep Recevierscited by 0
  6. 2024Theoretical Corrections and the Leveraging of Reinforcement Learning to Enhance Triangle Attackcited by 0
  7. 2025SDN-Based False Data Detection With Its Mitigation and Machine Learning Robustness for In-Vehicle Networkscited by 0
  8. 2025Protecting the Neural Networks against FGSM Attack Using Machine Unlearningcited by 0
  9. 2025Studying Various Activation Functions and Non-IID Data for Machine Learning Model Robustnesscited by 0
  10. 2026Comparative Insights on Adversarial Machine Learning from Industry and Academia: A User-Study Approachcited by 0
  11. 2026SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directionscited by 0