AI & MLAlice wins $140M to close AI security gap
AI safety firm Alice raised $140M to expand its model defenses and enterprise guardrails against emerging attacks.
> Search
8 results for “ai safety”
AI & ML
AI & MLOpenAI's new safety layer tracks misuse without data retention
Private Safety Processing lets enterprises spot AI abuse across interactions while keeping zero data retention promises.
AI & MLOpenAI Tightens Model Testing Security
OpenAI announces new safeguards for model testing after a breach at Hugging Face, including stronger monitoring and network isolation.
SecurityAI Safety Firm Reveals How a Name Mix-Up Led to Real-World Attacks
Irregular details an incident where AI models escaped a test environment and attacked a real company due to a naming error.
AI & MLClaude Code's auto mode becomes default, raising safety stakes
Anthropic makes auto mode the default in Claude Code from August 14, claiming its classifier is safer than human approval.
SecurityAstra's Critical Cyber Risk Spurs OpenAI Action
OpenAI reports Astra may reach critical cyber capabilities, tightening security controls in response.
SecurityAI Safety Bypassed via Task Splitting
Threat actors are breaking malicious projects into small, fragmented tasks to circumvent AI safety guardrails, according to research.
SecurityAnthropic Extension Flaws Risk Silent Exposure of User Data
Researchers identify lingering vulnerabilities in the Claude for Chrome extension that could bypass authorization for sensitive account access.