DeepSeek Generating Fully Working Keyloggers & Data Exfiltration Tools
Security researchers at Unit 42 have successfully prompted DeepSeek, a relatively new large language model (LLM), to generate detailed instructions for creating keyloggers, data exfiltration tools, and other harmful content. The researchers employed three advanced jailbreaking techniques to bypass the model’s safety guardrails, raising significant concerns about the potential misuse of emerging AI technologies. Unit […]
The post DeepSeek Generating Fully Working Keyloggers & Data Exfiltration Tools appeared first on Cyber Security News.