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

EU Regulatory Changes

1476 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: Statistical Analysis of Executability and Program Equivalence in Decompilation for IoT Vulnerability Detection
This publication presents a statistical analysis of decompilation techniques used to detect vulnerabilities in Internet of Things (IoT) devices. The research evaluates how reliably decompiled code ...
Read analysis →
arXiv: Casting the Net! Revisiting MasterFace Impersonation Attacks
A new academic paper, titled Casting the Net! Revisiting MasterFace Impersonation Attacks, has been published on arXiv, presenting an updated analysis of a known biometric security vulnerability. T...
Read analysis →
arXiv: When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse
A new research paper, titled "When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse," has been published on arXiv. The paper identifies a novel vulnerability in Retrieva...
Read analysis →
arXiv: Rigid-Covert GNSS Spoofing of UAV Swarms: A Structural Blind Spot, Its Detection Limit, and Absolute-Anchor De...
arXiv: SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains
arXiv: Understanding and Improving Model Editing for Secure Code Generation
arXiv: MIFA: An MILP-based Framework for Improving Differential Fault Attacks
arXiv: When Coordination Becomes a Threat: Communication Attacks in LLM-Controlled Multi-Robot Systems
arXiv: POKEx: Performance analysis of POKE-key exchange and SIDH-variants
arXiv: On a General Theoretical Framework for Radio Frequency Fingerprint-Based Authentication
arXiv: LoRAScan: Detecting Backdoor Prompts in Low-Rank Adapters for Large Language Models via Down-Projection Activa...
arXiv: Retrieval-Constrained Policy Optimization for Attack Technique Extraction from Cyber Threat Intelligence
arXiv: Tight Security for BBS Signatures
arXiv: Policy-Masked Private Experts: Auditable and Reversible Capability Access Control in Sparse MoE Models
arXiv: Resource-Aware Intrusion Detection in Infrastructure Networks: A Game-Theoretic Approach
arXiv: CyberLLM: A Multi-Agent LLM Framework for Autonomous Detection and Guarded Response in Automotive Cybersecurity
arXiv: From Documentation to Zero-day Vulnerabilities: LLM-Driven Fuzzing of JavaScript Engines in PDF Readers
arXiv: WhiteNet: Robust Identification of Overlapping IEEE 802.11 Signals Across Unseen Channels
arXiv: A Sound Translation from Tamarin to ProVerif: Enabling Comparative Analysis
A new academic paper, published on arXiv, presents a formal method for translating security protocol analyses between two leading verification tools, Tamarin and ProVerif. This is not a regulatory ...
Read analysis →
arXiv: Game Hopping in Lean
The publication introduces a novel technique called Game Hopping, a method for verifying the correctness and security properties of software systems by translating them into formal game-based proof...
Read analysis →