Researchers at the University of Missouri have developed an AI-powered method to detect hidden hardware trojans in chip designs, offering a 97% accurate solution. The approach leverages large language models to scan for suspicious code and provides explanations for detected threats.
A Penn State research team proposes a new information-filtering approach to predict future health information needs of online community participants. The approach incorporates user profiles, past posts and replies to categorize online content and provide more personalized healthcare resources.
Researchers at MIT's CSAIL have developed a new way to train neural networks that provide not only predictions and classifications but also rationales for their decisions. The system consists of two modules: one extracts segments of text from training data and scores them, while the other performs prediction or classification tasks.