Software Reliability Engineering News Today

Six AI tools, including OpenAI’s ChatGPT, were exploited to write code capable of damaging commercial databases – although OpenAI appears to have now fixed the vulnerability

A study by researchers from the University of Sheffields Department of Computer Science found that it was possible to manipulate chatbots into creating code capable of breaching other systems.

ChatGPT and other AI systems could be exploited to launch global cyber attacks, a University of Sheffield study has found.

 E-Mail IMAGE: The research team at National Institute of Informatics developed a technique to search automatically for simulation configurations that test various behaviors of automated driving systems. This research was conducted under... view more  Credit: © National Institute of Informatics The research team led by Fuyuki Ishikawa at the National Institute of Informatics (NII, Japan) developed a technique to search automatically for simulation configurations that test various beh...