P
Peter A. Beerel
Researcher at University of Southern California
Publications - 236
Citations - 3784
Peter A. Beerel is an academic researcher from University of Southern California. The author has contributed to research in topics: Asynchronous communication & Computer science. The author has an hindex of 30, co-authored 208 publications receiving 3403 citations. Previous affiliations of Peter A. Beerel include Intel & University of California, San Diego.
Papers
More filters
Proceedings ArticleDOI
TriLock: IC Protection with Tunable Corruptibility and Resilience to SAT and Removal Attacks
TL;DR: TriLock is proposed, a sequential logic locking method that can achieve high, tunable functional corruptibility while still guaranteeing exponential queries to the SAT solver in a SAT-based attack and adopts a state re-encoding method to obscure the boundary between the original state registers and those inserted by the locking method, thus making it more difficult to detect and remove the locking-related components.
Proceedings ArticleDOI
PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices
Yang Hu,Connor Imes,Xuanang Zhao,Souvik Kundu,Peter A. Beerel,Stephen P. Crago,John Paul Walters +6 more
TL;DR: PipeEdge as mentioned in this paper proposes a distributed framework for edge systems that uses pipeline parallelism to both speed up inference and enable running larger, more accurate models that otherwise cannot fit on single edge devices.
Proceedings ArticleDOI
GF-Flush: A GF(2) Algebraic Attack on Dynamically Secured Scan Chains
TL;DR: In this article, the authors propose a finite field GF(2)-based flush attack that breaks even the most rigorous version of state-of-the-art dynamic defenses, which can recover the key as long as 500 bits in less than 7 seconds.
Proceedings ArticleDOI
Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between Accuracy and Robustness of DNNs
TL;DR: SMART as discussed by the authors proposes a sparse mixture once for all adversarial training (SMART) model that allows a model to train once and then in-situ trade-off between accuracy and robustness, that too at a reduced compute and parameter overhead.
Journal ArticleDOI
Deep-n-Cheap: An Automated Efficient and Extensible Search Framework for Cost-Effective Deep Learning
Sourya Dey,Sara Babakniya,Saikrishna C. Kanala,Marco Paolieri,Leana Golubchik,Peter A. Beerel,Keith M. Chugg +6 more
TL;DR: Deep-n-Cheap as mentioned in this paper is an open-source automated machine learning (AutoML) search framework for deep learning models, which includes both architecture and training hyperparameters and supports convolutional neural networks and multi-layer perceptrons.