Joshua Berkowitz Anthropic Expands Bug Bounty Program to Strengthen AI Safety Anthropic is taking a bold step in AI safety by inviting the world’s top security researchers to put its latest defenses to the test. Their new bug bounty program aims to uncover serious vulnerabiliti... AI safety Anthropic bug bounty CBRN Claude 3.7 Sonnet Constitutional Classifiers Responsible Scaling security research
Joshua Berkowitz How Parser Differentials Led to a Major SAML SSO Authentication Bypass Authentication Turned on Its Head Imagine logging in as anyone you choose—simply by exploiting a flaw in how a system verifies SAML SSO responses. This became a reality thanks to a critical vulnerabil... authentication bug bounty ruby-saml SAML security vulnerability XML parsing
