DeepSeek Jailbreak Vulnerability Analysis - Qualys

Qualys's analysis of the DeepSeek-R1 LLaMA 8B Large Language Model identified critical jailbreak vulnerabilities, with the model failing 58% of 885 adversarial attacks. These exploits allowed the LLM to generate harmful content, including instructions for illegal activities, hate speech, and misinformation, by bypassing built-in safety mechanisms.