mlsanityData to 14 Oct 2026

Robustness and Cybersecurity in the EU Artificial Intelligence Act

arXiv 2502.16184 ↗First posted 22 Feb 2025cs.AI cs.CR cs.CYcited by 11

Not on the map. Why?

Abstract (arXiv)

The EU Artificial Intelligence Act (AIA) establishes different legal principles for different types of AI systems. While prior work has sought to clarify some of these principles, little attention has been paid to robustness and cybersecurity. This paper aims to fill this gap. We identify legal challenges and shortcomings in provisions related to robustness and cybersecurity for high-risk AI systems(Art. 15 AIA) and general-purpose AI models (Art. 55 AIA). We show that robustness and cybersecurity demand resilience against performance disruptions. Furthermore, we assess potential challenges in implementing these provisions in light of recent advancements in the machine learning (ML) literature. Our analysis informs efforts to develop harmonized standards, guidelines by the European Commission, as well as benchmarks and measurement methodologies under Art. 15(2) AIA. With this, we seek to bridge the gap between legal terminology and ML research, fostering a better alignment between research and implementation efforts.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 58 of its 121 references that are in the map. First posted on arXiv 22 Feb 2025.

Builds on

58 of 121 references.

References · 58

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  5. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  7. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  8. 2018Robustness May Be at Odds with Accuracycited by 880
  9. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  10. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  11. 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 454
  12. 2017Algorithmic decision making and the cost of fairnesscited by 403
38 more
  1. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  2. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 333
  3. 2020Performative Predictioncited by 327
  4. 2023Certifying LLM Safety against Adversarial Promptingcited by 266
  5. 2018Adversarial Robustness Toolbox v1.0.0cited by 215
  6. 2018Online Learning: A Comprehensive Surveycited by 205
  7. 2019Causality matters in medical imagingcited by 193
  8. 2018Delayed Impact of Fair Machine Learningcited by 184
  9. 2023Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injectioncited by 157
  10. 2020Understanding and Mitigating the Tradeoff Between Robustness and Accuracycited by 149
  11. 2020A Survey of Privacy Attacks in Machine Learningcited by 146
  12. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  13. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
  14. 2020Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attackscited by 116
  15. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 111
  16. 2023Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluationscited by 97
  17. 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Spacecited by 91
  18. 2024Red-Teaming for Generative AI: Silver Bullet or Security Theater?cited by 83
  19. 2020Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithmscited by 64
  20. 2020How Do Fair Decisions Fare in Long-term Qualification?cited by 60
  21. 2023Red Teaming Language Model Detectors with Language Modelscited by 55
  22. 2022Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contextscited by 53
  23. 2021A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?cited by 48
  24. 2019Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effectscited by 43
  25. 2019Equal Opportunity in Online Classification with Partial Feedbackcited by 35
  26. 2023A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutionscited by 35
  27. 2018Setting up a Reinforcement Learning Task with a Real-World Robotcited by 33
  28. 2024Generative AI in EU Law: Liability, Privacy, Intellectual Property, and Cybersecuritycited by 21
  29. 2021Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classificationcited by 20
  30. 2021The King is Naked: on the Notion of Robustness for Natural Language Processingcited by 16
  31. 2022Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantificationcited by 16
  32. 2017Fairer and more accurate, but for whom?cited by 13
  33. 2022Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Makingcited by 13
  34. 2023A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systemscited by 13
  35. 2023One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisionscited by 12
  36. 2025Unlocking the Black Box: Analysing the EU Artificial Intelligence Act's Framework for Explainability in AIcited by 11
  37. 2021Robustness and Reliability When Training With Noisy Labelscited by 10
  38. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 9

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 10.

11 papers.

  1. 2026High-Risk AI Systems and the Problem of Identity in the European AI Actcited by 4
  2. 2026Using predictive multiplicity to measure individual performance within the AI Actcited by 2
  3. 2026Computational Compliance for AI Regulation: Blueprint for a New Research Domaincited by 1
  4. 2026Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflectionscited by 1
  5. 2025Position: EU AI Act's Research Exemptions Can Break the Publication Norms of Major AI Conferencescited by 0
  6. 2026Now You See Me: Designing Responsible AI Dashboards for Early-Stage Health Innovationcited by 0
  7. 2026Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testingcited by 0
  8. 2026Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interfacecited by 0
  9. 2026Governance-as-Code: Translating EU AI Act Technical Requirements into Executable Compliance Pipelines for Generative AI Systemscited by 0
  10. 2026An Empirical Study and Assessment of EU AI Act Compliance Checkerscited by 0
  11. 2026Actionable Meta-Requirements for AI Robustness Auditingcited by 0