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

EU Regulatory Changes

668 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: What You See Is Not What You Execute: Memory-Based Runtime SBOM Generation for Supply Chain Security
This paper, published on arXiv, introduces a novel approach to software supply chain security called memory-based runtime Software Bill of Materials (SBOM) generation. It addresses a critical gap: ...
Read analysis →
arXiv: A quantum algorithm for one-shot signatures
arXiv: Optimal Small Set Expanders and Their Codes
arXiv: A Watermark for Vision-Language-Action and World Action Models
arXiv: TROPT: An Open Framework for Unifying and Advancing Discrete Text Optimization
arXiv: An Automated Framework for Input Alphabet Construction in Stateful Protocol Implementation Learning
arXiv: Detecting Malicious Agent Skills in the Wild using Attention
arXiv: OptChain: Achieving Optimal Throughput of Permissionless Blockchains
arXiv: FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
arXiv: TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger
arXiv: Exposing the Illusion of Erasure in Knowledge Editing for LLMs
arXiv: Quantum Key Distribution Without Shared Reference Frame Under Unital Noise
arXiv: A Hybrid Intrusion Detection System for Electric Vehicle Charging Infrastructure
arXiv: The EVerest Dataset for Secure Software Engineering
arXiv: Rising From the Ashes: How Agentic AI is Unblocking Challenges in Cybersecurity
arXiv: Understanding the (In)Security of Vibe-Coded Applications
arXiv: Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
arXiv: From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning
This paper, published on arXiv, reveals a significant privacy vulnerability in federated learning for large language models. It demonstrates that while federated learning is designed to protect dat...
Read analysis →
arXiv: Sovereign Execution Brokers: Enforcing Certificate-Bound Authority in Agentic Control Planes
This paper, published on arXiv, introduces a new technical framework called Sovereign Execution Brokers, which proposes a method for enforcing certificate-bound authority in AI agentic control plan...
Read analysis →
arXiv: Efficient and Sound Probabilistic Verification for AI Agents
This publication introduces a novel probabilistic verification framework for AI agents, designed to formally assess the safety and reliability of autonomous decision-making systems. The authors pro...
Read analysis →