Machine learning (ML) privacy concerns continue to surface, as audits show that models can reveal parts of the labels (the user’s choice, expressed preference, or the result of an action) used during training. A new research paper explores a different way to measure this risk, and the authors present findings that may change how companies test their models for leaks. Why standard audits have been hard to use Older privacy audits often relied on altering … More →
The post New observational auditing framework takes aim at machine learning privacy leaks appeared first on Help Net Security.
This week’s threat landscape (Week 48) reveals a surge in newly reported vulnerabilities, enhanced malware capabilities, and increasingly refined social-engineering […]
The post Weekly Threat Landscape Digest – Week 48 appeared first on HawkEye.
The Shai Hulud 2.0 worm, first detected on November 24, 2025, has compromised nearly 1,200 organizations, including major banks, government bodies, and Fortune 500 technology firms. While initial reports described it as a simple npm supply chain attack that flooded GitHub with spam repositories, new analysis reveals a far more sophisticated operation. Entro Security researchers […]
The post Shai Hulud 2.0 Compromises 1,200+ Organizations, Exposing Critical Runtime Secrets appeared first on Cyber Security News.