2 citations · 3 across the 7 of their papers we have counts for
7 papers
Investigating The Security of Modern AI and Cloud Infrastructure
Andrew Adiletta
The widespread deployment of Deep Neural Networks and Large Language Models (LLMs) relies on a foundational assumption of isolation that this dissertation challenges. This work sys…
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…
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…
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.…
Mayhem: Targeted Corruption of Register and Stack Variables
Andrew J. Adiletta, M. Caner Tol, Yarkın Doröz +1
In the past decade, many vulnerabilities were discovered in microarchitectures which yielded attack vectors and motivated the study of countermeasures. Further, architectural and p…
Don't Knock! Rowhammer at the Backdoor of DNN Models
M. Caner Tol, Saad Islam, Andrew J. Adiletta +2
State-of-the-art deep neural networks (DNNs) have been proven to be vulnerable to adversarial manipulation and backdoor attacks. Backdoored models deviate from expected behavior on…