
certified-unlearning-neural-networks-icml-2025
Code for the paper Certified Unlearning for Neural Networks, ICML 2025
ai-securitypapers-researchprivacy
12

Code for the paper Certified Unlearning for Neural Networks, ICML 2025

Security Advisory: Stored Cross-Site Scripting Via Agent Messages Leading To Session Token Theft (openclaw-dashboard)

EU AI Act compliance scanner for GitLab CI/CD pipelines — detects AI/ML libraries and posts risk classification as MR comments.

vllm-project vllm version 0.5.2.2 is vulnerable to Denial of Service attacks.

CVE-2026-73678 — MindsDB Minds Platform unauthenticated RCE via scratchpad exec (CVSS 10.0). Verified end-to-end with real LLM

OpenMed < 1.5.2 unauthenticated RCE via PII privacy-filter model loading and trust_remote_code=True