EU Regulatory Changes

A new ransomware incident has been publicly reported involving the Italian business services company BASE SPA. The attack was claimed by the threat group known as Spacebears and published on the ra...

This publication, titled "Shortest Path Problem with Subnormal Gaussian Fuzzy Costs," is a theoretical computer science paper from arXiv, not a regulatory change. It proposes a new mathematical mod...

This publication introduces a novel methodology for prioritizing cybersecurity alerts generated by Intrusion Detection Systems (IDS) using a mathematical approach called Subnormal Gaussian Fuzzy Mo...

This publication, titled Landseer: Exploring the Machine Learning Defense Landscape, is a technical research paper from arXiv that maps current adversarial attack and defense methods for machine le...

A new preprint from arXiv, titled "Do Modern Post-Hoc Watermarking Methods Beat Broken-Arrows?" published on May 26, 2026, evaluates the robustness of current AI-generated content watermarking tech...

This paper, published on arXiv, introduces BAIT, a new technical framework for improving the safety of large language models (AI systems). BAIT stands for Boundary-Guided Disclosure Escalation via ...

This paper, published on arXiv, presents research on a hidden cost associated with a specific technique used to make large language models (LLMs) forget or "unlearn" problematic data, such as copyr...

A new research paper, "Lessons from Penetration Tests on Large-Scale Agent Systems," has been published on arXiv, detailing systematic security vulnerabilities found in autonomous AI agent systems....

This paper, published on arXiv, presents a new evaluation framework for detecting prompt injection attacks against large language models. The key finding is that no single detection method works un...