7 papers
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…
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…
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…
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.…
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…
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…