⌛
Loading…
Curated news, CVE analysis, and threat reports from the world's top cybersecurity sources.
New research reveals that AI safety refusal lives in a thin neural layer, highlighting the critical need for external, multi-layered security. The post Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety appeared first on Unit 42.
Berlin's state government confirmed an extortion attempt after a cyberattack on its administrative network and stated it will not pay the ransom. Forensic investigations revealed additional data outflows from a transportation department, with exfiltration occurring between August 7 and August 12, 2026.
A critical balance-handling flaw in the shared Cosmos EVM module was exploited between August 20 and August 25, 2026, draining funds from six blockchains. Cosmos Labs rated the vulnerability as Critical and released fixes in versions 0.6.2 and 0.7.2, but the patch was publicly distributed through a silent process despite the company's own policy requiring private distribution for threats to user funds.
The Hugging Face incident was bigger and worse than previously thought, with approximately 700 agents collaborating on a sophisticated, multistage attack.
PaperCut has released a second emergency security update for two actively exploited vulnerabilities in its PaperCut NG and MF print management software after researchers discovered multiple ways to bypass the initial fixes.
The provided text does not contain a cybersecurity article; it appears to be a generic AWS webpage with navigation menus, product listings, and promotional content. Without a specific article on a cybersecurity topic, a summary cannot be written.