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

EU Regulatory Changes

1550 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 31 Jul 2026 arxiv_cscr
arXiv: Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Agent Harness Distillation: Inference-Time Harness Extraction and Exploitation in Autonomous Multi-Agent Systems
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Checking Information Flow in Cloud-based IoT Access Control Policies (Extended Version)
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Driving up Inference Energy on SNNs: Per-Sample and Universal Sponge Attacks
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Benign on Label, Malicious by Design: Clean-Label Dormant-to-Activated Backdoor via Machine Unlearning with Re...
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Adaptive Security at the Edge for 6G-Enabled Healthcare IoT
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: CHARGE: Leveraging CWE Hierarchies for Hardware Security SystemVerilog Assertion Generation
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Distributed Point Functions and Function Secret Sharing
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Strategy Phasing of Cyber Attacks on Digital Substations
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: Revisiting the Adversarial Robustness of Graph-Based Traffic Forecasting
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: AnchorMark: Robust Diffusion Watermarking via Latent-Space Rotation Synchrony
AI_SAFETY 31 Jul 2026 arxiv_cscr
arXiv: ThreatForest: Multi-Agent Attack Tree Generation with Pluggable TTP Framework Mapping
AI_SAFETY 30 Jul 2026 arxiv_cscr
arXiv: Function Privatization in the Local Model
This paper, published on arXiv under the AI Safety framework, introduces a new cryptographic technique called "Function Privatization" designed for the local differential privacy model. The core ch...
Read analysis →
AI_SAFETY 30 Jul 2026 arxiv_cscr
arXiv: On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
This paper, published on arXiv in July 2026, introduces a novel technical approach called "On-Policy Distillation" for improving the safety of large language models (LLMs). Rather than retraining a...
Read analysis →
AI_SAFETY 30 Jul 2026 arxiv_cscr
arXiv: MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair
This publication introduces MemSecBench, a new benchmark framework designed to systematically test and measure memory poisoning vulnerabilities in AI agents. Memory poisoning occurs when an attacke...
Read analysis →
AI_SAFETY 30 Jul 2026 arxiv_cscr
arXiv: HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models
This paper, published on arXiv, presents a new benchmark called HoF-Bench, which demonstrates that open-source, non-frontier AI models can rediscover real-world, previously AI-discovered Common Vul...
Read analysis →
AI_SAFETY 30 Jul 2026 arxiv_cscr
arXiv: AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents
A new research paper, AgentSnare, has been published on arXiv that introduces a framework for defending against autonomous penetration testing agents. This is not a regulatory change itself, but it...
Read analysis →