Evaluation of Prompt Injection Defenses in Large Language Models

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense configurations across more than 20,000 attacks. Every defense tha...

Lexmark Printers Improper Validation of Integrity Check Value (CVE-2023-50738)

A new feature to prevent Firmware downgrades was recently added to some Lexmark products. A method to override this downgrade protection has been identified. Lexmark documentation recommends that access to the Firmware Updates be restricted to trusted personnel. %NASLMINLEVEL 80900 C Tenable, Inc...