collaborators

7 papers

cs.CR2026

Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses

Kemal Derya, Berk Sunar

Defending large language models (LLMs) against jailbreak attacks, such as Greedy Coordinate Gradient (GCG), remains a challenge, particularly under adaptive threat models where an…

cs.CR2025

Super Suffixes: Bypassing Text Generation Alignment and Guard Models Simultaneously

Andrew Adiletta, Kathryn Adiletta, Kemal Derya +1

The rapid deployment of Large Language Models (LLMs) has created an urgent need for enhanced security and privacy measures in Machine Learning (ML). LLMs are increasingly being use…

cs.CR2025

Rubber Mallet: A Study of High Frequency Localized Bit Flips and Their Impact on Security

Andrew Adiletta, Zane Weissman, Fatemeh Khojasteh Dana +2

The increasing density of modern DRAM has heightened its vulnerability to Rowhammer attacks, which induce bit flips by repeatedly accessing specific memory rows. This paper present…

cs.CR2025

LeapFrog: The Rowhammer Instruction Skip Attack

Andrew Adiletta, M. Caner Tol, Kemal Derya +2

Since its inception, Rowhammer exploits have rapidly evolved into increasingly sophisticated threats compromising data integrity and the control flow integrity of victim processes.…

cs.CR2025

Spill The Beans: Exploiting CPU Cache Side-Channels to Leak Tokens from Large Language Models

Andrew Adiletta, Berk Sunar

Side-channel attacks on shared hardware resources increasingly threaten confidentiality, especially with the rise of Large Language Models (LLMs). In this work, we introduce Spill…

cs.LG2025

Non-Halting Queries: Exploiting Fixed Points in LLMs

Ghaith Hammouri, Kemal Derya, Berk Sunar

We introduce a new vulnerability that exploits fixed points in autoregressive models and use it to craft queries that never halt. More precisely, for non-halting queries, the LLM n…