A comprehensive study by Palo Alto Networks’ Unit 42 has revealed that 17 popular generative AI web applications remain vulnerable to various jailbreaking techniques. These vulnerabilities potentially allow malicious actors to bypass AI safety mechanisms to extract sensitive information or generate harmful content. The research, effective as of November 10, 2024, tested both single-turn and […]
The post Researchers Jailbreaked 17 Popular LLM Models To Communicate Sensitive Data appeared first on Cyber Security News.
This article has been indexed from Cyber Security News