Currently free during beta - premium features coming soon. Subscribe now to lock in early access.
AI_SAFETY

EU Regulatory Changes

1501 changes tracked across 24 compliance frameworks including DORA, NIS2, GDPR, EU AI Act, Cyber Resilience Act, and more.

All DORA NIS2 GDPR CSRD MaRisk ISO27001 EU_AI_ACT CRA DSA DMA eIDAS2 SOC2 PCI_DSS HIPAA ISO42001 AMLD6 PSD3 DATA_ACT GPSR CER EUDR CVE BREACH AI_SAFETY
arXiv: Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries
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...
Read analysis →
arXiv: BlowLive: Blow-Based Multi-Factor Biometrics with Liveness Detection and Revocability
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 ...
Read analysis →
arXiv: Do (Not) Tell Me About My Insecurities: Assessing the Status Quo of Coordinated Vulnerability Disclosure in Ge...
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...
Read analysis →
arXiv: A Tattered Cloak of Invisibility: Measuring Anonymity Loss in Railgun on Ethereum
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...
Read analysis →
arXiv: The Web4 Agent Economy: A Large-Scale Empirical Study of the Landscape, Challenges, and Opportunities
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...
Read analysis →
arXiv: Automated Detection of Configuration-Specific Security Vulnerabilities via Patch Analysis
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...
Read analysis →
arXiv: Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks
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...
Read analysis →
arXiv: Can Machine Learning Break Wi-Fi Privacy? A Study on MAC Address Randomization
arXiv: Space-based Missile Defense
arXiv: RAS: Measuring LLM Safety Through Refusal Alignment
arXiv: Shoot the Honey, Cloak the Player: Towards Zero-Runtime-Overhead Proactive Defense and Detection for Visual Ga...
arXiv: Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution
arXiv: Taxonomy of Risks on Automated Fact-Checking Systems Considering its Propagation
arXiv: TL++: Accuracy and Privacy Preserving Traversal Learning for Distributed Intelligent Systems
arXiv: Probabilistic Agents in Deterministic Audits: Evaluating Multi-Agent Systems for Automated Audits Based on the...
arXiv: An Approach for a Supporting Multi-LLM System for Automated Certification Based on the German IT-Grundschutz
arXiv: Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks
arXiv: CrypFormBench: Benchmarking Formal Analysis Capability of Large Language Models for Cryptographic Schemes
arXiv: Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Direction...
arXiv: How Reliable Is Your Jailbreak Judge? Calibration and Adversarial Robustness of Automated ASR Scoring