AI_SAFETY
EU Regulatory Changes
1525 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
A new mathematical paper has been published on arXiv, titled "Rank-Two Frobenius-Linearized Normal Forms and Orthoderivative Dual Coordinates in Quadratic APN Maps." This is a theoretical research ...
Read analysis →
A new research paper, ToolHazard, has been published on arXiv, introducing a framework for creating large-scale adversarial environments to test the security and alignment of large language model (...
Read analysis →
A new research paper, published on arXiv, examines how Chinese-origin vision-language models (VLMs) are designed to shift from outright refusal of sensitive prompts to a strategy of "reframing" res...
Read analysis →
This publication introduces a novel framework for run-time cybersecurity in AI systems, focusing on control-flow anomaly detection and hardware-level monitoring. It proposes a model-based approach ...
Read analysis →
arXiv: AmbSentry: Mitigating Sensing Eavesdropping in ISAC Systems by Harnessing Ambient IoT Devices
A new technical paper, AmbSentry, proposes a method to reduce the risk of sensing eavesdropping in Integrated Sensing and Communication (ISAC) systems by using ambient Internet of Things (IoT) devi...
Read analysis →
A new academic paper, titled Instruction Alignment for Binary Code Representation Learning, has been published on arXiv. The research proposes a method to improve how machine learning models unders...
Read analysis →
A new academic paper, published on arXiv, introduces a technique for fingerprinting text-to-image diffusion models by exploiting a phenomenon called collapsed generation. This method can identify w...
Read analysis →