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
arXiv: Taming the Security-Energy Paradox: A Green AI Approach to Optimized Android Malware Detection
This paper, published on arXiv, presents a novel approach to Android malware detection that balances security effectiveness with energy efficiency, a concept termed the "security-energy paradox." I...
Read analysis →
arXiv: HijackKV: New Threat in Position-Independent KV Cache Reuse
A new research paper, "HijackKV: New Threat in Position-Independent KV Cache Reuse," published on arXiv, identifies a novel security vulnerability in large language model (LLM) inference systems. T...
Read analysis →
arXiv: JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
This publication introduces JANUS, a novel framework designed to predict latent safety risks in AI agents operating over extended time horizons. Unlike existing safety tools that focus on immediate...
Read analysis →
arXiv: Defense Against LLM Backdoors using Critical Neuron Isolation Pruning
This paper, published on arXiv on July 22, 2026, introduces a new technical method for defending large language models (LLMs) against backdoor attacks. The technique, called Critical Neuron Isolati...
Read analysis →
arXiv: Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation
arXiv: Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents
arXiv: DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection
arXiv: An Automated Framework for Extracting Reachable Attack Chains from Cyber Threat Intelligence Reports
arXiv: GhostPrompt: Cross-Image Adversarial Prompt for Vision-Language Models
arXiv: FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense
arXiv: Twin Agent: Context Residual Compression for Privilege Separated Agents
arXiv: Examining User Behavior and Cognitive Biases in Personal Password Security
arXiv: End-to-End Differential Privacy in Training Deep Neural Network Classifiers
arXiv: When HTTP 402 Meets the Blockchain: Risks on Emerging x402 Payments
arXiv: Integrity of peer-to-peer distributed LLM inference under malicious nodes
arXiv: Chi-MERA: Defending Orbit-Based Authentication of LEO Satellites with the Space Oddity of MLAT (Long Version)
This publication, a pre-print research paper from arXiv, presents a novel machine learning technique called Chi-MERA designed to enhance the security of satellite authentication systems. It specifi...
Read analysis →
arXiv: SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement
This paper, published on arXiv, introduces a new technical framework called SFGA, or Statistics-First Gating Architecture with Adjudicative Escalation, designed to improve the trustworthiness of da...
Read analysis →
arXiv: Tracing the Shadows: Automatic Tracking and Analysis of Crypto Money Laundering via Transaction Semantic Analysis
This publication from July 2026 introduces a novel methodology for automatically detecting and tracking crypto money laundering by analyzing the semantic meaning of transactions, rather than just r...
Read analysis →
arXiv: Data Leakage Prevention in Agentic Applications via Preemptive Hardening
This publication introduces a technical framework for preventing data leakage in agentic AI systems—autonomous software agents that can act on behalf of users. The paper proposes a method called "p...
Read analysis →
arXiv: Private Approximation of Graph Spectra and Cuts via Spectral Amplifiers
This publication from arXiv, dated July 21, 2026, introduces a new algorithmic method for privately approximating graph spectra and cuts using spectral amplifiers. While the paper is a technical co...
Read analysis →