Related papers: "Energon": Unveiling Transformers from GPU Power a…

Side-channel vulnerabilities pose an increasing threat to cryptographically protected devices. Consequently, it is crucial to observe information leakages through physical parameters such as power consumption and electromagnetic (EM)…

Modern processors are highly optimized systems where every single cycle of computation time matters. Many optimizations depend on the data that is being processed. Software-based microarchitectural attacks exploit effects of these…

Existing tools to detect side-channel attacks on Intel SGX are grounded on the observation that attacks affect the performance of the victim application. As such, all detection tools monitor the potential victim and raise an alarm if the…

Federated Learning (FL) enables collaborative model training across distributed devices while safeguarding data and user privacy. However, FL remains susceptible to privacy threats that can compromise data via direct means. That said,…

Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tasks. In this paper, we identify a novel security threat…

In this work, we make two contributions towards understanding of in-context learning of linear models by transformers. First, we investigate the adversarial robustness of in-context learning in transformers to hijacking attacks -- a type of…

Transformer architectures have revolutionized machine learning across a wide range of domains, from natural language processing to scientific computing. However, their growing deployment in high-stakes applications, such as computer vision,…

GPUs are increasingly being used in security applications, especially for accelerating encryption/decryption. While GPUs are an attractive platform in terms of performance, the security of these devices raises a number of concerns. One…

Transformer-based malware detection systems operating on graph modalities such as control flow graphs (CFGs) achieve strong performance by modeling structural relationships in program behavior. However, their robustness to adversarial…

Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients of the models shared in training. Previous attacks…

Cache side channel attacks are increasingly alarming in modern processors due to the recent emergence of Spectre and Meltdown attacks. A typical attack performs intentional cache access and manipulates cache states to leak secrets by…

Graphics processing units (GPUs) are becoming an essential part of the intelligent transportation system (ITS) for enabling video-based and artificial intelligence (AI) based applications. GPUs provide high-throughput and energy-efficient…

To improve efficiency, nearly all parallel processing units (CPUs and GPUs) implement relaxed memory models in which memory operations may be re-ordered, i.e., executed out-of-order. Prior testing work in this area found that memory…

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

Transformer architecture has widespread applications, particularly in Natural Language Processing and computer vision. Recently Transformers have been employed in various aspects of time-series analysis. This tutorial provides an overview…

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Side Channel Analysis (SCA) presents a clear threat to privacy and security in modern computing systems. The vast majority of communications are secured through cryptographic algorithms. These algorithms are often provably-secure from a…

Recent work has highlighted the risks of intellectual property (IP) piracy of deep learning (DL) models from the side-channel leakage of DL hardware accelerators. In response, to provide side-channel leakage resiliency to DL hardware…

Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary…

Machine learning, with its myriad applications, has become an integral component of numerous technological systems. A common practice in this domain is the use of transfer learning, where a pre-trained model's architecture, readily…