Robustness and Cybersecurity in the EU Artificial Intelligence Act

arXiv:2502.16184 · cs.AI, cs.CR, cs.CY, cs.LG · Submitted 2025-02-22 · Read on arXiv

cs.AI, cs.CR, cs.CY, cs.LG

Submitted: 2025-02-22

Updated: 2026-10-10

Project page: https://secml2018.github.io

Terminology

• Robustness — 4× in this paper · explained in 5 episodes
• EU Artificial Intelligence Act — 2× in this paper
• Alignment — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
• Towards Robust Recommendation: A Review and an Adversarial Robustness Evaluation Library
• Fairer and more accurate, but for whom?
• A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?
• Gemini: A Family of Highly Capable Multimodal Models
• Machine Learning with Multi-Site Imaging Data: An Empirical Study on the Impact of Scanner Effects
• Adversarial Robustness Toolbox v1.0.0
• GPT-4 Technical Report
• Hierarchical Text-Conditional Image Generation with CLIP Latents
• Intriguing properties of neural networks

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems