Related papers: GPUHammer: Rowhammer Attacks on GPU Memories are P…

Machine learning based malware detection techniques rely on grayscale images of malware and tends to classify malware based on the distribution of textures in graycale images. Albeit the advancement and promising results shown by machine…

Machine learning models are routinely deployed on a wide range of computing hardware. Although such hardware is typically expected to produce identical results, differences in its design can lead to small numerical variations during…

Side-channel attacks on memory (SCAM) exploit unintended data leaks from memory subsystems to infer sensitive information, posing significant threats to system security. These attacks exploit vulnerabilities in memory access patterns, cache…

Federated Learning (FL) has emerged as a powerful paradigm for collaborative model training while keeping client data decentralized and private. However, it is vulnerable to Data Reconstruction Attacks (DRA) such as "LoKI" and "Robbing the…

The rapid adoption of large language models (LLMs) in critical domains has spurred extensive research into their security issues. While input manipulation attacks (e.g., prompt injection) have been well studied, Bit-Flip Attacks (BFAs) --…

Graphics processing units (GPUs) are gaining widespread use in computational chemistry and other scientific simulation contexts because of their huge performance advantages relative to conventional CPUs. However, the reliability of GPUs in…

Reading or writing outside the bounds of a buffer is a serious security vulnerability that has been exploited in numerous occasions. These attacks can be prevented by ensuring that every buffer is only accessed within its specified bounds.…

Scientific applications produce vast amounts of data, posing grand challenges in the underlying data management and analytic tasks. Progressive compression is a promising way to address this problem, as it allows for on-demand data…

Graph Neural Networks(GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions. Existing trigger generators are often simplistic in structure and overly reliant on specific…

The initial location of data in DRAMs is determined and controlled by the 'address-mapping' and even modern memory controllers use a fixed and run-time-agnostic address mapping. On the other hand, the memory access pattern seen at the…

Backdoor attacks have been considered a severe security threat to deep learning. Such attacks can make models perform abnormally on inputs with predefined triggers and still retain state-of-the-art performance on clean data. While backdoor…

GPU compilers are complex software programs with many optimizations specific to target hardware. These optimizations are often controlled by heuristics hand-designed by compiler experts using time- and resource-intensive processes. In this…

Microarchitectural timing attacks exploit subtle timing variations caused by hardware behaviors to leak sensitive information. In this paper, we introduce MCHammer, a novel side-channel technique that leverages machine clears induced by…

Deep Generative Models (DGMs) are a popular class of deep learning models which find widespread use because of their ability to synthesize data from complex, high-dimensional manifolds. However, even with their increasing industrial…

Graph neural networks (GNNs) have recently emerged as a promising learning paradigm in learning graph-structured data and have demonstrated wide success across various domains such as recommendation systems, social networks, and electronic…

Recent research has constructed successful graph reconstruction attack (GRA) on GFL. But these attacks are still challenged in aspects of effectiveness and stealth. To address the issues, we propose the first Data Manipulation aided…

GPUs have become indispensable in high-performance computing, machine learning, and many other domains. Efficiently utilizing the memory subsystem on GPUs is critical for maximizing computing power through massive parallelism. Analyzing…

Diffusion Models (DMs) have achieved remarkable success in image generation, yet recent studies reveal their vulnerability to backdoor attacks, where adversaries manipulate outputs via covert triggers embedded in inputs. Existing defenses,…

Programming errors, defective hardware components (such as hard disk spindle defects), and environmental hazards can lead to invalid memory operations. In addition, less predictable forms of environmental stress, such as radiation, thermal…

One intriguing property of deep neural networks (DNNs) is their inherent vulnerability to backdoor attacks -- a trojan model responds to trigger-embedded inputs in a highly predictable manner while functioning normally otherwise. Despite…