EU Regulatory Changes

This paper, published on arXiv in June 2026, proposes a novel technical framework called the "Unfireable Safety Kernel" for ensuring AI alignment at execution time. It addresses a critical gap in c...

This paper, published on arXiv, introduces a new technical framework called "Detect, Unlearn, Restore" (DUR) designed to defend text summarization models against data poisoning attacks. Data poison...

This paper, published on arXiv, presents an empirical study of the ERC-8004 decentralized AI agent ecosystem, focusing on the practical trustworthiness of so-called "trustless" agents. It does not ...

This paper, published on arXiv, presents a new privacy vulnerability specific to attention layers in tabular foundation models. It demonstrates that an attacker can infer sensitive attributes of hi...

A new research paper, BlowLive, has been published on arXiv proposing a biometric authentication system that uses breath patterns as a multi-factor identifier, combined with liveness detection and ...

This paper, published on arXiv, assesses the current state of Coordinated Vulnerability Disclosure (CVD) in Germany against the backdrop of new EU cybersecurity regulations, particularly the NIS2 D...

A new academic paper published on arXiv, titled "A Tattered Cloak of Invisibility: Measuring Anonymity Loss in Railgun on Ethereum," presents empirical analysis showing that the Railgun privacy pro...

This publication is not a regulatory change but a research paper from arXiv that provides a large-scale empirical study of the emerging "Web4 Agent Economy," where autonomous AI agents perform task...

A new research paper published on arXiv proposes a method for automatically detecting security vulnerabilities that are specific to particular software configurations, using patch analysis. The stu...

A new research paper published on arXiv, titled "Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks," presents findings that could have significant implications for AI safet...