mlsanityData to 7 Oct 2026

Adversarial Machine Learning -- Industry Perspectives

arXiv 2002.05646 ↗First posted 4 Feb 2020cs.CY cs.CR cs.LGcited by 121

Not on the map. Why?

Cited by 23 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Based on interviews with 28 organizations, we found that industry practitioners are not equipped with tactical and strategic tools to protect, detect and respond to attacks on their Machine Learning (ML) systems. We leverage the insights from the interviews and we enumerate the gaps in perspective in securing machine learning systems when viewed in the context of traditional software security development. We write this paper from the perspective of two personas: developers/ML engineers and security incident responders who are tasked with securing ML systems as they are designed, developed and deployed ML systems. The goal of this paper is to engage researchers to revise and amend the Security Development Lifecycle for industrial-grade software in the adversarial ML era.

Key facts. Cited by 121 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 25; 2023: 32; 2024: 24; 2025: 16; 2026: 8.

121 papers.

Sort:

By area:

  1. 2021Black-box Detection of Backdoor Attacks with Limited Information and Datacited by 71
  2. 2022A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarkscited by 70
  3. 2021Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Trainingcited by 58
  4. 2021Reliable Adversarial Distillation with Unreliable Teacherscited by 55
  5. 2022"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practicecited by 55
  6. 2023TrojanPuzzle: Covertly Poisoning Code-Suggestion Modelscited by 47
  7. 2021Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networkscited by 37
  8. 2021PointBA: Towards Backdoor Attacks in 3D Point Cloudcited by 34
  9. 2022Identifying a Training-Set Attack's Target Using Renormalized Influence Estimationcited by 32
  10. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  11. 2022Energy-Latency Attacks via Sponge Poisoningcited by 29
  12. 2024Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attackcited by 26
38 more
  1. 2022COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attackscited by 25
  2. 2022Indiscriminate Data Poisoning Attacks on Neural Networkscited by 24
  3. 2022Machine Learning Security against Data Poisoning: Are We There Yet?cited by 23
  4. 2023Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attackscited by 23
  5. 2021What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoningcited by 22
  6. 2023Analyzing And Editing Inner Mechanisms Of Backdoored Language Modelscited by 22
  7. 2023A Meta-Summary of Challenges in Building Products with ML Components -- Collecting Experiences from 4758+ Practitionerscited by 22
  8. 2022The Role of Machine Learning in Cybersecuritycited by 21
  9. 2022Machine Learning Security in Industry: A Quantitative Surveycited by 21
  10. 2022Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attackscited by 20
  11. 2023Backdoor Attack with Sparse and Invisible Triggercited by 20
  12. 2022How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?cited by 17
  13. 2022An Equivalence Between Data Poisoning and Byzantine Gradient Attackscited by 16
  14. 2023Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifierscited by 14
  15. 2025DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillationcited by 14
  16. 2026The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggerscited by 13
  17. 2021AI Ethics Principles in Practice: Perspectives of Designers and Developerscited by 12
  18. 2022Image and Model Transformation with Secret Key for Vision Transformercited by 12
  19. 2022DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learningcited by 11
  20. 2022Holistic Adversarial Robustness of Deep Learning Modelscited by 11
  21. 2023A Survey on Malware Detection with Graph Representation Learningcited by 11
  22. 2021Accumulative Poisoning Attacks on Real-time Datacited by 10
  23. 2021The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?cited by 9
  24. 2022Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learningcited by 9
  25. 2022Threat Assessment in Machine Learning based Systemscited by 9
  26. 2023SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion Detectioncited by 9
  27. 2023Understanding the robustness difference between stochastic gradient descent and adaptive gradient methodscited by 8
  28. 2023Bucks for Buckets (B4B): Active Defenses Against Stealing Encoderscited by 8
  29. 2024Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Controlcited by 8
  30. 2024Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractorscited by 8
  31. 2022Reducing Certified Regression to Certified Classification for General Poisoning Attackscited by 7
  32. 2022Multi-SpacePhish: Extending the Evasion-space of Adversarial Attacks against Phishing Website Detectors using Machine Learningcited by 7
  33. 2023Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defensecited by 7
  34. 2021Evaluating the Cybersecurity Risk of Real World, Machine Learning Production Systemscited by 6
  35. 2023AI Maintenance: A Robustness Perspectivecited by 6
  36. 2023Large Scale Foundation Models for Intelligent Manufacturing Applications: A Surveycited by 6
  37. 2024A Method to Facilitate Membership Inference Attacks in Deep Learning Modelscited by 6
  38. 2024Active Fourier Auditor for Estimating Distributional Properties of ML Modelscited by 6

50 most cited of 121 All 121 (JSON)