How SW and HW Vulnerabilities Can Complement LLM-Specific Algorithmic Attacks (UT Austin, Intel et al.)
Stay on top of this story
Follow the names and topics behind it.
Add this story's key topics to your watchlist so LyscoNews can highlight related developments and future matches.
Create a free account to sync your watchlist, saved stories, and alerts across devices.
Quick Summary
A new technical paper, “Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems,” was published by the University of Texas, Austin, Intel Labs, Symmetry Systems, Microsoft and Georgia Tech. Abstract “Rapid progress in generative AI has given rise to Compound AI systems – pipelines comprised of multiple large language models (LLM),... » read more The post How SW and HW Vulnerabilities Can Complement LLM-Specific Algorithmic Attacks (UT Austin, Intel et al.) appeared first on Semiconductor Engineering.