Tasked with writing an application for a US defense contractor, the model made the code 19% more likely to be hackable.
The post Chinese AI Model Writes More Hackable Code When Told It’s for US Contractor 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.
