Every entry below was pulled directly from a regulator’s feed in the last few days — CELLAR, EBA, ESMA, ENISA, BSI, BaFin, ANSSI and 14 other sources — classified against 21 EU compliance frameworks and summarised. Updates daily.
AI_SAFETYarxiv_cscr20 Jul 2026
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 benchmark simulates…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Optimal Domain-Aware Privacy Mechanisms for Synthetic Data Generation
This paper, published on arXiv, proposes a new technical framework for generating synthetic data that is specifically designed to preserve privacy while maintaining domain-specific utility. It introduces "optimal…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
A new research paper published on arXiv on July 20, 2026, titled "Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?" examines vulnerabilities in self-hosted AI agents where an attacker can…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: RT-SHCUA: Real-Time Self-Hosted Computer-Use Agent for UAV Control
This publication introduces a new technical framework, RT-SHCUA, which enables real-time, self-hosted control of unmanned aerial vehicles (UAVs) through an artificial intelligence agent. The system operates without…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Rate-Distortion Function for Encrypted Traffic Side-Channel Defense
This publication introduces a novel theoretical framework for defending against side-channel attacks on encrypted network traffic, using rate-distortion theory to balance privacy protection with data utility. The paper…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Residual Observability and Attack Detectability in Encrypted OPC UA Traffic
This paper, published on arXiv, presents a new method for detecting cyberattacks on encrypted OPC UA traffic, a common industrial communication protocol. It demonstrates that even when traffic is encrypted, certain…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models
This paper, published on arXiv on July 20, 2026, presents a technical analysis of vulnerabilities in Vision-Language-Action (VLA) models, which are AI systems that process visual and language inputs to perform physical…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation
A new preprint from arXiv, titled "Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation," published on 20 July 2026, presents evidence that large language models (LLMs) used for…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Protecting Floating-Point Computation for DNN Binaries with MBA Obfuscation
This publication from arXiv presents a new technique for obfuscating floating-point computations within deep neural network (DNN) binaries using Mixed Boolean-Arithmetic (MBA) obfuscation. The paper details a method to…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Detection, Attribution, Narration: An End-to-End Pipeline for Explainable Money Mule Identification
A new research paper published on arXiv proposes an end-to-end pipeline for detecting, attributing, and narrating money mule activities using explainable AI. The framework, titled "Detection, Attribution, Narration: An…
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Quantum-Resilient Banking Transaction Security using DW-HKEM: A Hybrid RSA/ML-KEM Cryptographic Gateway with Real-Time
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: (A)iSpy: Parasitic Trojans for Machine Learning Infrastructure
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Salience Induction against Multi-Hop RAG Agents: Threat and Defense
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Isolation Failure From Shared Storage: Characterizing and Exploiting Page-Cache SCA Leakage Across Containers and VMs
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: ShadowPickle: Evading Machine Learning Model Scanners via Stealthy Pickle Deserialization Attacks
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: The Duality of Information Flow: Reconciling Robust Downgrading with Non-Interference
AI_SAFETYarxiv_cscr19 Jul 2026
arXiv: Measuring and Evaluating the Performance of Generative AI Models for Scam Detection
AI_SAFETYarxiv_cscr19 Jul 2026
arXiv: Physical Time-Lock Puzzles
AI_SAFETYarxiv_cscr19 Jul 2026
arXiv: Learning-Driven Adaptive Audit Scheduling: A Sequential Decision Approach to Off-Chain Data Integrity
AI_SAFETYarxiv_cscr19 Jul 2026
arXiv: Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models
AI_SAFETYarxiv_cscr19 Jul 2026
arXiv: SpexPay: A Privacy-Preserving Pay-As-You-Go System for Dynamic Spectrum Sharing
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: Hardware Robustness of Sample-Based Quantum Diagonalization
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: CutBackdoor: A Circuit Cut Triggered Backdoor Attack on Variational Quantum Algorithms
AI_SAFETYarxiv_cscr20 Jul 2026
arXiv: GARAGE: Characterizing the Automation Boundary in LLM-based Attack Graph Generation
CRAransomwarelive20 Jul 2026
Ransomware: incransom claims Ali-Monde (US) — Not Found
BREACHransomwarelive20 Jul 2026
Ransomware: safepay claims wdk.de (DE) — Not Found
BREACHransomwarelive20 Jul 2026
Ransomware: safepay claims jaecklin-industrial.de (DE) — Manufacturing
BREACHransomwarelive20 Jul 2026
Ransomware: safepay claims lbb-treuhand.de (DE) — Business Services
BREACHransomwarelive20 Jul 2026
Ransomware: safepay claims timetex.de (DE) — Business Services