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

EU Regulatory Changes

371 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
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: DP-SAPF: Saliency-Aware Parameter Fine-tuning of Public Models for Differentially Private Image Synthesis
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: bpK#: Delegatable Pseudonyms And Their Applications to National eID Systems
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: A Bayesian Approach to Membership Inference for Statistical Release
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Privacy-Enhanced Zero-Order Federated Learning via xMK-CKKS over Wireless Channels
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration ...
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Fingerprinting Inference Systems of Large Language Models
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Ciphera: A Decentralised Biometric Identity Framework
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive ...
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
AI_SAFETY 30 May 2026 arxiv_cscr
arXiv: Secure Distributed Hypothesis Testing
AI_SAFETY 28 May 2026 arxiv_cscr
arXiv: Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Re...
This paper, published on arXiv, introduces a new benchmark called "Code as a Weapon," which is a curated set of prompts designed to test whether large language models (LLMs) that generate code will...
Read analysis →
AI_SAFETY 28 May 2026 arxiv_cscr
arXiv: Efficient and Quantum-safe Internet Key Exchange Protocols for Satellite Communications
This publication from May 2026 introduces a new technical framework for Internet Key Exchange (IKE) protocols designed to be resistant to quantum computing attacks, specifically tailored for satell...
Read analysis →
AI_SAFETY 28 May 2026 arxiv_cscr
arXiv: MaskClaw: Edge-Side Personalized Privacy Arbitration for GUI Agents with Behavior-Driven Skill Evolution
This paper, published on arXiv, introduces MaskClaw, a technical framework designed to enhance privacy for graphical user interface (GUI) agents—AI systems that interact with software interfaces on...
Read analysis →
AI_SAFETY 28 May 2026 arxiv_cscr
arXiv: GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction
A new research paper, GraphSteal, published on arXiv, demonstrates a novel method for extracting the structural knowledge embedded within Graph-based Retrieval-Augmented Generation (RAG) systems. T...
Read analysis →