Cato Networks discovers a new LLM jailbreak technique that relies on creating a fictional world to bypass a model’s security controls.
The post New Jailbreak Technique Uses Fictional World to Manipulate AI appeared first on SecurityWeek.
New CCA Jailbreak Method Works Against Most AI Models
Two Microsoft researchers have devised a new jailbreak method that bypasses the safety mechanisms of most AI systems.
The post New CCA Jailbreak Method Works Against Most AI Models appeared first on SecurityWeek.
DeepSeek Compared to ChatGPT, Gemini in AI Jailbreak Test
DeepSeek’s susceptibility to jailbreaks has been compared by Cisco to other popular AI models, including from Meta, OpenAI and Google.
The post DeepSeek Compared to ChatGPT, Gemini in AI Jailbreak Test appeared first on SecurityWeek.
DeepSeek Security: System Prompt Jailbreak, Details Emerge on Cyberattacks
Researchers found a jailbreak method that exposed DeepSeek’s system prompt, while others have analyzed the DDoS attacks aimed at the new gen-AI.
The post DeepSeek Security: System Prompt Jailbreak, Details Emerge on Cyberattacks appeared first on SecurityWeek.
ChatGPT, DeepSeek Vulnerable to AI Jailbreaks
Different research teams have demonstrated jailbreaks against ChatGPT, DeepSeek, and Alibaba’s Qwen AI models.
The post ChatGPT, DeepSeek Vulnerable to AI Jailbreaks appeared first on SecurityWeek.
DeepSeek Blames Disruption on Cyberattack as Vulnerabilities Emerge
China’s DeepSeek blamed sign-up disruptions on a cyberattack as researchers started finding vulnerabilities in the R1 AI model.
The post DeepSeek Blames Disruption on Cyberattack as Vulnerabilities Emerge appeared first on SecurityWeek.
Microsoft Details ‘Skeleton Key’ AI Jailbreak Technique
Microsoft has tricked several gen-AI models into providing forbidden information using a jailbreak technique named Skeleton Key.
The post Microsoft Details ‘Skeleton Key’ AI Jailbreak Technique appeared first on SecurityWeek.