5 papers
SeFoRA: Sketch-Aggregated Federated Low-Rank Adaptation with Heterogeneous Client Ranks
Yue Xia, Tayyebeh Jahani-Nezhad, Mayank Bakshi +1
We consider federated parameter efficient fine-tuning of large neural networks with low-rank adaptation (LoRA,~Hu et al.\ 2022). Combining LoRA with federated PEFT introduces chall…
Sequential Adversarial Hypothesis Testing
Eeshan Modak, Mayank Bakshi, Bikash Kumar Dey +1
We study the adversarial binary hypothesis testing problem in the sequential setting. Associated with each hypothesis is a closed, convex set of distributions. Given the hypothesis…
Using Preformed Resistive Random Access Memory to Create a Strong Physically Unclonable Function
Jack Garrard, John F. Hardy, Carlo daCunha +1
Physically Unclonable Functions (PUFs) are a promising solution for identity verification and asymmetric encryption. In this paper, a new Resistive Random Access Memory (ReRAM) PUF…
Hypothesis Testing for Adversarial Channels: Chernoff-Stein Exponents
Eeshan Modak, Neha Sangwan, Mayank Bakshi +2
We study the Chernoff-Stein exponent of the following binary hypothesis testing problem: Associated with each hypothesis is a set of channels. A transmitter, without knowledge of t…
Byzantine-Resilient Zero-Order Optimization for Communication-Efficient Heterogeneous Federated Learning
Maximilian Egger, Mayank Bakshi, Rawad Bitar
We introduce CyBeR-0, a Byzantine-resilient federated zero-order optimization method that is robust under Byzantine attacks and provides significant savings in uplink and downlink…