activity
20172026
most citedSPOILER: Speculative Load Hazards Boost Rowhammer and Cache Attacks

41 citations · 164 across the 18 of their papers we have counts for

collaborators
Showing cs.CRShow all

23 papers · 1 filter

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

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.CR2025

μRL: Discovering Transient Execution Vulnerabilities Using Reinforcement Learning

M. Caner Tol, Kemal Derya, Berk Sunar

We propose using reinforcement learning to address the challenges of discovering microarchitectural vulnerabilities, such as Spectre and Meltdown, which exploit subtle interactions…

cs.CR2024

FAULT+PROBE: A Generic Rowhammer-based Bit Recovery Attack

Kemal Derya, M. Caner Tol, Berk Sunar

Rowhammer is a security vulnerability that allows unauthorized attackers to induce errors within DRAM cells. To prevent fault injections from escalating to successful attacks, a wi…