Prompt Injection
-
Amazon opens invite-only bug bounty for NOVA models to outside researchers
Amazon has launched an invite-only bug bounty program for its NOVA family of language models, allowing select researchers to test and be paid for findings on issues such as prompt injection, jailbreaking and other vulnerabilities, with the company saying the effort will help secure models integrated across Amazon and customer systems.
-
Researchers disclose three now-patched vulnerabilities in Google’s Gemini AI
Researchers disclosed three patched vulnerabilities in Google’s Gemini AI that could have exposed users to privacy risks, affecting Cloud Assist, the Search Personalization model and the Browsing Tool, Tenable said; Google has applied mitigations.
-
Threat actors weaponize HexStrike AI to exploit recently disclosed vulnerabilities, Check Point warns
Threat actors are weaponizing HexStrike AI, an AI-driven offensive security tool, to exploit recently disclosed vulnerabilities, prompting Check Point to urge immediate patching and hardening of affected systems.
-
Google Enhances AI Security with Layered Defenses Against Prompt Injection Attacks
Google has taken significant steps to enhance the security of its generative AI systems by implementing layered defenses against indirect prompt injections, which pose a new cybersecurity risk. These measures include advanced filtering techniques and a proactive approach to preventing malicious user inputs.
-
Security Flaw in GitLab’s AI Assistant Exposes Source Code to Attackers
A significant vulnerability in GitLab’s AI coding assistant, Duo, has been discovered, allowing potential theft of source code and injection of malicious instructions, prompting urgent security measures from GitLab.
