46 citations · 133 across the 34 of their papers we have counts for
18 papers · 1 filter
EVAX: Towards a Practical, Pro-active & Adaptive Architecture for High Performance & Security
Samira Mirbagher Ajorpaz, Daniel Moghimi, Jeffrey Neal Collins +3
This paper provides an end-to-end solution to defend against known microarchitectural attacks such as speculative execution attacks, fault-injection attacks, covert and side channe…
PAGE404: Breaking GPU Isolation Through Hardware-assisted Page Migration
Ravan Nazaraliyev, Yicheng Zhang, Nael Abu-Ghazaleh
NVIDIA's Grace Hopper (GH200) superchip represents a new generation of heterogeneous computing, tightly integrating a 72-core Arm-based CPU with a Hopper GPU on a single module via…
Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs
Md Abdullah Al Mamun, Ngoc Phu Doan, Pedram Zaree +2
Large Language Models are increasingly trained on proprietary or sensitive data, from private healthcare and financial records to user conversations containing secrets. Ensuring th…
Evil Vizier: Vulnerabilities of LLM-Integrated XR Systems
Yicheng Zhang, Zijian Huang, Sophie Chen +3
Extended reality (XR) applications increasingly integrate Large Language Models (LLMs) to enhance user experience, scene understanding, and even generate executable XR content, and…
ShadowScope: GPU Monitoring and Validation via Composable Side Channel Signals
Ghadeer Almusaddar, Yicheng Zhang, Saber Ganjisaffar +4
As modern systems increasingly rely on GPUs for computationally intensive tasks such as machine learning acceleration, ensuring the integrity of GPU computation has become critical…
Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots
Erfan Shayegani, G M Shahariar, Sara Abdali +3
Multimodal Language Models (MMLMs) typically undergo post-training alignment to prevent harmful content generation. However, these alignment stages focus primarily on the assistant…
NVBleed: Covert and Side-Channel Attacks on NVIDIA Multi-GPU Interconnect
Yicheng Zhang, Ravan Nazaraliyev, Sankha Baran Dutta +3
Multi-GPU systems are becoming increasingly important in highperformance computing (HPC) and cloud infrastructure, providing acceleration for data-intensive applications, including…
Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment
Pedram Zaree, Md Abdullah Al Mamun, Quazi Mishkatul Alam +3
Recent research has shown that carefully crafted jailbreak inputs can induce large language models to produce harmful outputs, despite safety measures such as alignment. It is impo…
Siren Song: Manipulating Pose Estimation in XR Headsets Using Acoustic Attacks
Zijian Huang, Yicheng Zhang, Sophie Chen +2
Extended Reality (XR) experiences involve interactions between users, the real world, and virtual content. A key step to enable these experiences is the XR headset sensing and esti…
I Know What You Sync: Covert and Side Channel Attacks on File Systems via syncfs
Cheng Gu, Yicheng Zhang, Nael Abu-Ghazaleh
Operating Systems enforce logical isolation using abstractions such as processes, containers, and isolation technologies to protect a system from malicious or buggy code. In this p…
Beyond the Bridge: Contention-Based Covert and Side Channel Attacks on Multi-GPU Interconnect
Yicheng Zhang, Ravan Nazaraliyev, Sankha Baran Dutta +3
High-speed interconnects, such as NVLink, are integral to modern multi-GPU systems, acting as a vital link between CPUs and GPUs. This study highlights the vulnerability of multi-G…
That Doesn't Go There: Attacks on Shared State in Multi-User Augmented Reality Applications
Carter Slocum, Yicheng Zhang, Erfan Shayegani +3
Augmented Reality (AR) is expected to become a pervasive component in enabling shared virtual experiences. In order to facilitate collaboration among multiple users, it is crucial…
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
Erfan Shayegani, Yue Dong, Nael Abu-Ghazaleh
We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modalit…
Jedi: Entropy-based Localization and Removal of Adversarial Patches
Bilel Tarchoun, Anouar Ben Khalifa, Mohamed Ali Mahjoub +2
Real-world adversarial physical patches were shown to be successful in compromising state-of-the-art models in a variety of computer vision applications. Existing defenses that are…
Defending with Errors: Approximate Computing for Robustness of Deep Neural Networks
Amira Guesmi, Ihsen Alouani, Khaled N. Khasawneh +4
Machine-learning architectures, such as Convolutional Neural Networks (CNNs) are vulnerable to adversarial attacks: inputs crafted carefully to force the system output to a wrong l…
Spy in the GPU-box: Covert and Side Channel Attacks on Multi-GPU Systems
Sankha Baran Dutta, Hoda Naghibijouybari, Arjun Gupta +3
The deep learning revolution has been enabled in large part by GPUs, and more recently accelerators, which make it possible to carry out computationally demanding training and infe…
ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints
Amira Guesmi, Khaled N. Khasawneh, Nael Abu-Ghazaleh +1
Advances in deep learning have enabled a wide range of promising applications. However, these systems are vulnerable to Adversarial Machine Learning (AML) attacks; adversarially cr…
Defensive Approximation: Securing CNNs using Approximate Computing
Amira Guesmi, Ihsen Alouani, Khaled Khasawneh +4
In the past few years, an increasing number of machine-learning and deep learning structures, such as Convolutional Neural Networks (CNNs), have been applied to solving a wide rang…