Geek-Guy.com

Tag: scores

AI models more vulnerable than claimed when faced with iterative attacks

CISOs relying on LLM runtime guardrails and official safety scores when making security decisions about their organizations’ AI usage and model selection are due for a wakeup call. According to a new study from Cisco, frontier models from OpenAI, Anthropic, Google, xAI, and Amazon have significantly worse risk profiles when pressured in multi-turn attacks compared…

NIST Scales Back Vulnerability Scoring in 2026 as CVE Volume Surges

The National Institute of Standards and Technology (NIST) is narrowing how it analyzes and scores software vulnerabilities, citing a sharp increase in submissions that has made it difficult to keep pace.  “For years, security teams relied on NVD for vulnerability context to support prioritization decisions. But that model is under real strain,” said Ian Gray,…