# Robustness and Cybersecurity in the EU Artificial Intelligence Act

arXiv: https://arxiv.org/abs/2502.16184 · HTML: https://mlsanity.com/paper/2502.16184/

## 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 (most cited first, 30 of 58)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning](https://mlsanity.com/paper/1712.05526/) (2017)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Multi-step Jailbreaking Privacy Attacks on ChatGPT](https://mlsanity.com/paper/2304.05197/) (2023)
- [Performative Prediction](https://mlsanity.com/paper/2002.06673/) (2020)
- [Certifying LLM Safety against Adversarial Prompting](https://mlsanity.com/paper/2309.02705/) (2023)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [Online Learning: A Comprehensive Survey](https://mlsanity.com/paper/1802.02871/) (2018)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [Delayed Impact of Fair Machine Learning](https://mlsanity.com/paper/1803.04383/) (2018)
- [Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection](https://mlsanity.com/paper/2307.16888/) (2023)
- [Understanding and Mitigating the Tradeoff Between Robustness and Accuracy](https://mlsanity.com/paper/2002.10716/) (2020)
- [A Survey of Privacy Attacks in Machine Learning](https://mlsanity.com/paper/2007.07646/) (2020)
- [To be Robust or to be Fair: Towards Fairness in Adversarial Training](https://mlsanity.com/paper/2010.06121/) (2020)
- [FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients](https://mlsanity.com/paper/2207.09209/) (2022)
- [Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks](https://mlsanity.com/paper/2006.12557/) (2020)
- [Robustness and Accuracy Could Be Reconcilable by (Proper) Definition](https://mlsanity.com/paper/2202.10103/) (2022)
- [Revisiting Out-of-distribution Robustness in NLP: Benchmark, Analysis, and LLMs Evaluations](https://mlsanity.com/paper/2306.04618/) (2023)
- [Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space](https://mlsanity.com/paper/2402.09063/) (2024)
- [Red-Teaming for Generative AI: Silver Bullet or Security Theater?](https://mlsanity.com/paper/2401.15897/) (2024)

## Built on by (most cited first, 11 of 11)

- [High-Risk AI Systems and the Problem of Identity in the European AI Act](https://mlsanity.com/paper/2605.23922/) (2026)
- [Using predictive multiplicity to measure individual performance within the AI Act](https://mlsanity.com/paper/2602.11944/) (2026)
- [Computational Compliance for AI Regulation: Blueprint for a New Research Domain](https://mlsanity.com/paper/2601.04474/) (2026)
- [Security, privacy, and agentic AI in a regulatory view: From definitions and distinctions to provisions and reflections](https://mlsanity.com/paper/2603.18914/) (2026)
- [Position: EU AI Act's Research Exemptions Can Break the Publication Norms of Major AI Conferences](https://mlsanity.com/paper/2506.03218/) (2025)
- [Now You See Me: Designing Responsible AI Dashboards for Early-Stage Health Innovation](https://mlsanity.com/paper/2602.23378/) (2026)
- [Auto-ART: Structured Literature Synthesis and Automated Adversarial Robustness Testing](https://mlsanity.com/paper/2604.20704/) (2026)
- [Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface](https://mlsanity.com/paper/2609.03420/) (2026)
- [Governance-as-Code: Translating EU AI Act Technical Requirements into Executable Compliance Pipelines for Generative AI Systems](https://mlsanity.com/paper/2609.20016/) (2026)
- [An Empirical Study and Assessment of EU AI Act Compliance Checkers](https://mlsanity.com/paper/2609.36228/) (2026)
- [Actionable Meta-Requirements for AI Robustness Auditing](https://mlsanity.com/paper/2610.14356/) (2026)

## 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.