Generative artificial intelligence tools, such as large language models like ChatGPT, are used nearly every day, yet they aren’t completely secure. Prompt injection attacks, where an attacker uses deceptive text to manipulate the outputs, are a risk that can change the model’s goals or cause data leaks.
Mozilla AI recently highlighted the PIGuard model developed in the lab of Ning Zhang, an associate professor of computer science and engineering in the McKelvey School of Engineering at Washington University in St. Louis, along with Chaowei Xiao, at Johns Hopkins University, and collaborators. They took the top spot among all models tested in a large experiment looking at open-source guard rails and agentic systems.
PIGuard was published in Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) last summer.
Read more on the McKelvey Engineering website.
