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: ContractHIL-HLS: Contract-Aligned Multi-Agent Workflow with Hardware-in-the-Loop Feedback for HLS Design
This paper, published on arXiv, introduces ContractHIL-HLS, a novel framework for designing hardware systems using multi-agent AI workflows. It integrates hardware-in-the-loop feedback to ensure th...
Read analysis →
arXiv: SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
arXiv: Does Runtime Topology Context Improve LLM-Generated Kubernetes Security Patches?
arXiv: \textsc{IH-Benchmark}: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications
arXiv: E-MagDiP: Electro-Magnetic based Differential Privacy for EEG based Community Sensing
arXiv: From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs
arXiv: Hermes: Low Tail-Latency Via Prefix Consensus
arXiv: Toward Standardized Cross-Vendor Agent Tool Trust Management in Autonomous Networks
arXiv: Stemma: Induced Decision Regions Reveal LLM Provenance
arXiv: Adversarial Deepfake Generation and an Investigation of Purification-Based Adversarial Detection
arXiv: Evaluation of Adversarial Robustness in Arabic Language Models
arXiv: A Structuration Approach to Theorizing Cybersecurity Practice: The STARC Model
arXiv: Verifiable blind probabilistic error cancellation
arXiv: SignDeepSC: A Semantic Signature-based Approach for Robust Semantic Communication
arXiv: SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents
arXiv: Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Ex...
arXiv: There Will Be Spam: Characterizing State-Invariant Transactions and Speculative MEV
A new academic paper published on arXiv, titled "There Will Be Spam: Characterizing State-Invariant Transactions and Speculative MEV," analyzes a specific class of blockchain transactions that are ...
Read analysis →
arXiv: A Cybersecurity MLPS Large Language Model with Multi-Path Retrieval Fusion
This publication introduces a new technical framework called MLPS, which stands for Multi-Path Retrieval Fusion, designed to improve the security and reliability of large language models used in cy...
Read analysis →
arXiv: Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation
This publication, titled "Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation," is a research paper from arXiv, not a formal regulatory change. It proposes a n...
Read analysis →
arXiv: ContainmentBench: Trace-Based Evaluation of Post-Injection Containment in Tool-Using LLM Agents
A new research paper, ContainmentBench, has been published on arXiv that introduces a trace-based evaluation framework for assessing how well tool-using large language model (LLM) agents can contai...
Read analysis →