4 papers
Survival of the Cheapest: Cost-Aware Hardware Adaptation for Adversarial Robustness
Charles Meyers, Mohammad Reza Saleh Sedghpour, Tommy Löfstedt +1
Deploying adversarially robust machine learning systems requires continuous trade-offs between robustness, cost, and latency. We present an autonomic decision-support framework pro…
Trust-Aware Routing for Distributed Generative AI Inference at the Edge
Chanh Nguyen, Erik Elmroth
Emerging deployments of Generative AI increasingly execute inference across decentralized and heterogeneous edge devices rather than on a single trusted server. In such environment…
Tiny, Hardware-Independent, Compression-based Classification
Charles Meyers, Aaron MacSween, Erik Elmroth +1
The recent developments in machine learning have highlighted a conflict between online platforms and their users in terms of privacy. The importance of user privacy and the struggl…
A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)
Charles Meyers, Mohammad Reza Saleh Sedghpour, Tommy Löfstedt +1
Machine learning models -- deep neural networks in particular -- have performed remarkably well on benchmark datasets across a wide variety of domains. However, the ease of finding…