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: Control Flow Graph Recovery for Dynamically Loaded Code via Symbolic Library Resolution
This paper, published on arXiv, presents a new technical method for recovering control flow graphs from dynamically loaded code using symbolic library resolution. While not a regulatory change itse...
Read analysis →
arXiv: LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion Models
This publication introduces LoRA-Key, a technical method for embedding invisible, user-specific watermarks into images generated by text-to-diffusion AI models. The paper proposes a system where ea...
Read analysis →
arXiv: Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection
This publication introduces a novel AI framework called Temporal Motif-aware Graph Test-time Adaptation, designed to detect anomalies in blockchain transactions that fall outside normal distributio...
Read analysis →
arXiv: KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing
This paper, published on arXiv, introduces a novel auditing method called KBF (Knowledge Boundary as Fingerprint) for evaluating the safety and reliability of large language models (LLMs) and their...
Read analysis →
arXiv: CODEFUSE-DEBENCH: An Empirical Study on Readability, Recompilability, and Functionality
This publication, CODEFUSE-DEBENCH, is a research paper from arXiv that presents a new benchmark for evaluating the safety and reliability of AI code generation models. It focuses on three key metr...
Read analysis →
arXiv: DP-SAPF: Saliency-Aware Parameter Fine-tuning of Public Models for Differentially Private Image Synthesis
arXiv: bpK#: Delegatable Pseudonyms And Their Applications to National eID Systems
arXiv: A Bayesian Approach to Membership Inference for Statistical Release
arXiv: Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
arXiv: BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse Autoencoders
arXiv: Privacy-Enhanced Zero-Order Federated Learning via xMK-CKKS over Wireless Channels
arXiv: How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration ...
arXiv: Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
arXiv: Fingerprinting Inference Systems of Large Language Models
arXiv: Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
arXiv: Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational Interaction
arXiv: Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection
arXiv: Ciphera: A Decentralised Biometric Identity Framework
arXiv: Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive ...
arXiv: AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security