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

EU Regulatory Changes

1649 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 22 Jul 2026 arxiv_cscr
arXiv: GLID: Gated Local Intrinsic Dimension Repairs the Blind Spots of Face-Forgery Detectors
This publication introduces GLID, a new method for detecting AI-generated or manipulated facial images, known as deepfakes. The research identifies a critical weakness in current face-forgery detec...
Read analysis →
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA
This paper, published on arXiv in July 2026, presents a diagnostic study evaluating the performance of small large language models (LLMs) on cybersecurity question-answering tasks. It introduces a ...
Read analysis →
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: When to Trust the Map: Confidence-Aware LLM Routing for Automotive CVE-to-ATM Mapping
This publication from July 2026 introduces a novel framework for using large language models to map automotive cybersecurity vulnerabilities (CVEs) to specific attack trees (ATMs) within the automo...
Read analysis →
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: Broken Gates: Re-evaluating Web Bot Defenses in the Age of LLM Agents
This paper, published on arXiv, presents a critical security analysis of web bot defenses in the context of advanced Large Language Model (LLM) agents. The authors demonstrate that current state-of...
Read analysis →
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: Attacking Graph Foundation Models Through Their Shared Representation
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: CryptanalysisBench: Can LLMs do Cryptanalysis?
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: PIP-NTT: Towards a Scalable Memory-Parallelized Accelerator for Iterative NTT in PQC
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: Towards an Automated Test of LLM Security Knowledge
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: 0-Cyclic Equalizability of Binary Words Characterized by Hamming Weight
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: SoK: Adversarial Robustness of the Variational Quantum Eigensolver via Red-Teaming
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: They'll Verify. They Just Won't Act. How Authority Framing and Laundered Code Turn a Trusted Agentic CI/CD Pip...
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: PTSan: A Practical Memory Safety Sanitizer for C/C++ with Pointer-Object Authority
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: Sarus: Privacy-Preserving Multi-Vendor Perception Fusion via Homomorphic Encryption
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: Code Division Modulation Layers Against Forgetting and Inference in Continual Gait Identification
AI_SAFETY 22 Jul 2026 arxiv_cscr
arXiv: Exploiting Load/Store Leakage of Sparse Vectors for Key Recovery in HQC
AI_SAFETY 21 Jul 2026 arxiv_cscr
arXiv: Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security
This paper, published on arXiv, introduces a new benchmark called Adaptive Adversaries designed to test the security of large language model (LLM) agents. Unlike previous single-turn tests, this be...
Read analysis →