46 citations · 133 across the 34 of their papers we have counts for
36 papers
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…
Visual Grounding Safety in Vision-Language Models
Erfan Shayegani, Kundan Krishna, Yue Dong +3
Vision-language models (VLMs) are increasingly trained to generate structured outputs like points and bounding boxes that downstream interfaces, agents, and robots can act on, yet…
Microflow: Microarchitectural Causal Observability for Deep Cross-Layer Analysis and Optimization
Saber Ganjisaffar, Chengyu Song, Nael Abu-Ghazaleh
Modern computer architecture relies heavily on simulation to identify bottlenecks and evaluate optimizations. However, existing microarchitectural performance analysis methods are…
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…
VLMs Need Words: Vision Language Models Ignore Visual Detail In Favor of Semantic Anchors
Haz Sameen Shahgir, Xiaofu Chen, Yu Fu +4
Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they often fail on tasks that require fine-grained visual perce…
AttenMIA: LLM Membership Inference Attack through Attention Signals
Pedram Zaree, Md Abdullah Al Mamun, Yue Dong +2
Large Language Models (LLMs) are increasingly deployed to enable or improve a multitude of real-world applications. Given the large size of their training data sets, their tendency…
Just Do It!? Computer-Use Agents Exhibit Blind Goal-Directedness
Erfan Shayegani, Keegan Hines, Yue Dong +6
Computer-Use Agents (CUAs) are an increasingly deployed class of agents that take actions on GUIs to accomplish user goals. In this paper, we show that CUAs consistently exhibit Bl…
Modeling Hierarchical Thinking in Large Reasoning Models
G M Shahariar, Erfan Shayegani, Ali Nazari +1
Large Reasoning Models (LRMs) solve complex tasks by generating long Chain-of-Thought (CoT) sequences; however, the emergent dynamics governing reasoning trajectories are not well…
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…
Poison Once, Refuse Forever: Weaponizing Alignment for Injecting Bias in LLMs
Md Abdullah Al Mamun, Ihsen Alouani, Nael Abu-Ghazaleh
Large Language Models (LLMs) are aligned to meet ethical standards and safety requirements by training them to refuse answering harmful or unsafe prompts. In this paper, we demonst…
PRACtical: Subarray-Level Counter Update and Bank-Level Recovery Isolation for Efficient PRAC Rowhammer Mitigation
Ravan Nazaraliyev, Saber Ganjisaffar, Nurlan Nazaraliyev +1
As DRAM density increases, Rowhammer becomes more severe due to heightened charge leakage, reducing the number of activations needed to induce bit flips. The DDR5 standard addresse…
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…
Analysis of Stable Vertex Values: Fast Query Evaluation Over An Evolving Graph
Mahbod Afarin, Chao Gao, Xizhe Yin +3
Evaluating a query over a large, irregular graph is inherently challenging. This challenge intensifies when solving a query over a sequence of snapshots of an evolving graph, where…
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…
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
Saketh Bachu, Erfan Shayegani, Rohit Lal +6
Vision-language models (VLMs) have improved significantly in their capabilities, but their complex architecture makes their safety alignment challenging. In this paper, we reveal a…
Cross-Modal Safety Alignment: Is textual unlearning all you need?
Trishna Chakraborty, Erfan Shayegani, Zikui Cai +5
Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing…
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…
Attention Deficit is Ordered! Fooling Deformable Vision Transformers with Collaborative Adversarial Patches
Quazi Mishkatul Alam, Bilel Tarchoun, Ihsen Alouani +1
The latest generation of transformer-based vision models has proven to be superior to Convolutional Neural Network (CNN)-based models across several vision tasks, largely attribute…
May the Noise be with you: Adversarial Training without Adversarial Examples
Ayoub Arous, Andres F Lopez-Lopera, Nael Abu-Ghazaleh +1
In this paper, we investigate the following question: Can we obtain adversarially-trained models without training on adversarial examples? Our intuition is that training a model wi…