activity
20242026
collaborators

11 papers

cs.PF2026

Performance and Cost-Aware Cache Provisioning

Ridwanul Tanvir, George Kesidis

While traditional cache policy evaluations fix capacity - often at 0.1% of the dataset - and measure the resulting hit rate, practical edge-cloud deployments require balancing both…

cs.CR2026

CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs

Zhengxing Li, David J. Miller, Guangmingmei Yang +1

While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.g. for images, there is a paucity of such methods for LLMs. First, the LLM i…

cs.LG2026

A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization

Guangmingmei Yang, David J. Miller, George Kesidis

Deep learning, which in general relies on voluminous amounts of training data, is vulnerable to data poisoning attacks, including error-generic attacks and backdoors (Trojans). In…

cs.LG2025

Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization

Guangmingmei Yang, David J. Miller, George Kesidis

Most post-training backdoor detection methods rely on attacked models exhibiting extreme outlier detection statistics for the target class of an attack, compared to non-target clas…

cs.PF2025

GPU Cluster Scheduling for Network-Sensitive Deep Learning

Aakash Sharma, Vivek M. Bhasi, Sonali Singh +3

We propose a novel GPU-cluster scheduler for distributed DL (DDL) workloads that enables proximity based consolidation of GPU resources based on the DDL jobs' sensitivities to the…

cs.LG2025

Inverting Trojans in LLMs

Zhengxing Li, Guangmingmei Yang, Jayaram Raghuram +2

While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM i…