How SW and HW Vulnerabilities Can Complement LLM-Specific Algorithmic Attacks (UT Austin, Intel et al.)


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), so... » read more

NIWeek on Offer in May


National Instruments is putting on its annual NIWeek conference and exhibition this month, May 21-24 at the Austin Convention Center in the capital of Texas. Details on the agenda and the full four-day program are available here. I’ve attended NIWeek for the past two years, and it’s an opportunity to learn new things, see impressive product demonstrations, and hear about developments ... » read more