activity
20242026
collaborators

14 papers

cs.CR2026

zkComposer: Decomposing Proof Construction to Scale zkML

Pawan Kumar Sanjaya, Christina Giannoula, Valdy Oktavian +4

Zero-knowledge machine learning (zkML) enables a server to perform verifiable inference while keeping model parameters private from the client. However, existing zkML systems incur…

cs.CR2026

AutoPRAC: Automating Attack Discovery for PRAC-Based Rowhammer Defenses using Model Checkers

Joyce Qu, Gururaj Saileshwar

Per-Row Activation Counting (PRAC) in DDR5 is a specification to mitigate Rowhammer attacks by tracking activations per row and triggering mitigative refreshes when needed. However…

cs.CR2026

GPUBreach: Privilege Escalation Attacks on GPUs using Rowhammer

Chris S. Lin, Yuqin Yan, Guozhen Ding +4

NVIDIA GPUs with GDDR memories have been shown susceptible to Rowhammer-based bit-flips, similar to CPUs. However, Rowhammer exploits on GPUs have been limited to injecting untarge…

cs.CL2026

When Speculation Spills Secrets: Side Channels via Speculative Decoding In LLMs

Jiankun Wei, Abdulrahman Abdulrazzag, Tianchen Zhang +2

Deployed large language models (LLMs) often rely on speculative decoding, a technique that generates and verifies multiple candidate tokens in parallel, to improve throughput and l…

cs.LG2025

CLIP: Client-Side Invariant Pruning for Mitigating Stragglers in Secure Federated Learning

Anthony DiMaggio, Raghav Sharma, Gururaj Saileshwar

Secure federated learning (FL) preserves data privacy during distributed model training. However, deploying such frameworks across heterogeneous devices results in performance bott…

cs.CR2025

PrisonBreak: Jailbreaking Large Language Models with at Most Twenty-Five Targeted Bit-flips

Zachary Coalson, Jeonghyun Woo, Chris S. Lin +8

We study a new vulnerability in commercial-scale safety-aligned large language models (LLMs): their refusal to generate harmful responses can be broken by flipping only a few bits…