y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#ml-security News & Analysis

4 articles tagged with #ml-security. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

4 articles
AIBearisharXiv – CS AI · Jun 57/10
🧠

Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

Researchers demonstrate a reinforcement learning approach that enables AI agents to learn and execute adversarial attacks on machine learning models more efficiently than traditional methods. The RL-based system achieves 13.2% higher attack success rates and reduces queries needed per attack by 16.9%, while outperforming state-of-the-art adversarial methods by 17% on unseen inputs, revealing a significant new security vulnerability in deployed ML systems.

AIBearisharXiv – CS AI · May 287/10
🧠

Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems

Researchers have identified critical vulnerabilities in machine learning-based fault detection systems used in cyber-physical infrastructure, demonstrating that backdoor attacks can compromise these safety-critical systems with poisoning rates as low as 10%. This threat directly impacts smart grids, industrial automation, and other essential infrastructure that increasingly rely on AI models for anomaly detection and system recovery.

AINeutralarXiv – CS AI · Jun 26/10
🧠

SECUREVENT: Hybrid AI/ML Security Monitoring for Distributed Event-Based Systems

SECUREVENT proposes a hybrid AI/ML security architecture for distributed event-based systems that combines cryptographic controls with anomaly detection and behavioral analysis. The system addresses vulnerabilities in publish/subscribe platforms, IoT networks, and microservices by monitoring complex event patterns that static rules cannot detect, demonstrating improved threat detection recall while maintaining low false-positive rates.