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: Physical Layer Authentication With Channel Knowledge Maps in Indoor Environments
This publication, dated June 25, 2026, presents a research paper on a novel method for physical layer authentication in indoor wireless networks using Channel Knowledge Maps. While not a regulatory...
Read analysis →
arXiv: Design and Performance Evaluation of Secure RF and WiFi-Based Communication in Drone Swarms via Testbed Implem...
This paper, published on arXiv, presents a technical study on the design and performance of secure radio frequency and WiFi communication protocols for drone swarms. It is not a regulatory change i...
Read analysis →
arXiv: ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
A new research paper, titled ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP, has been published on arXiv, detailing a novel adversarial attack targeting Model Context Proto...
Read analysis →
arXiv: Protocol Prying: Systematic Vulnerability Research in the Apple AirDrop and Android Quick Share Proximity Tran...
arXiv: Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhance...
arXiv: Chai: Agentic Discovery of Cryptographic Misuse Vulnerabilities
arXiv: A Deterministic Control Plane for LLM Coding Agents
arXiv: SpikeTimer: Exploring Active Copyright Protection in Spiking Neural Networks via Temporal Backdoor Regularization
arXiv: MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG
arXiv: MergeLLL: A Hierarchical Divide-and-Conquer Framework for LLL-Based Lattice Reduction
arXiv: DroidBreaker: Practical and Functional Problem-Space Attacks on Machine-Learning Android Malware Detectors
arXiv: The Fungible Reserve Standard: A Deterministic Framework for Encoding Carrying Costs in Asset-Backed Tokens
arXiv: TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems
arXiv: Autoformalization of Agent Instructions into Policy-as-Code
arXiv: Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
arXiv: Empirical Software Engineering TerraProbe: A Layered-Oracle Framework for Detecting Deceptive Fixes in LLM-Ass...
arXiv: Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision...
arXiv: The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
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...
Read analysis →
arXiv: Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning
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...
Read analysis →
arXiv: Can Trustless Agents Be Trusted? An Empirical Study of the ERC-8004 Decentralized AI Agent Ecosystem
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 ...
Read analysis →