Related papers: Lightning: Striking the Secure Isolation on GPU Cl…

Graphics Processing Units (GPUs) are deployed on most present server, desktop, and even mobile platforms. Nowadays, a growing number of applications leverage the high parallelism offered by this architecture to speed-up general purpose…

Over the past years, great progress has been made in improving the computing power of general-purpose graphics processing units (GPGPUs), which facilitates the prosperity of deep neural networks (DNNs) in multiple fields like computer…

Hyperscale large language model (LLM) inference places extraordinary demands on cloud systems, where even brief failures can translate into significant user and business impact. To better understand and mitigate these risks, we present one…

Previous research on selective protection for neural network components typically exploits only static vulnerability differences. Although these methods improve upon classical modular redundancy, they still incur substantial overhead for…

Fully Connected Neural Networks (FCNNs) have been the core of most state-of-the-art Machine Learning (ML) applications in recent years and also have been widely used for Intrusion Detection Systems (IDSs). Experimental results from the last…

Deep Neural Networks (DNNs) are well-known to be vulnerable to Adversarial Examples (AEs). A large amount of efforts have been spent to launch and heat the arms race between the attackers and defenders. Recently, advanced gradient-based…

Security of machine learning is increasingly becoming a major concern due to the ubiquitous deployment of deep learning in many security-sensitive domains. Many prior studies have shown external attacks such as adversarial examples that…

Graph Neural Networks (GNNs) have emerged as a prominent graph learning model in various graph-based tasks over the years. Nevertheless, due to the vulnerabilities of GNNs, it has been empirically shown that malicious attackers could easily…

Mobile edge devices see increased demands in deep neural networks (DNNs) inference while suffering from stringent constraints in computing resources. Split computing (SC) emerges as a popular approach to the issue by executing only initial…

Perturbation-based mechanisms, such as differential privacy, mitigate gradient leakage attacks by introducing noise into the gradients, thereby preventing attackers from reconstructing clients' private data from the leaked gradients.…

On-device inference of machine learning models for mobile phones is desirable due to its lower latency and increased privacy. Running such a compute-intensive task solely on the mobile CPU, however, can be difficult due to limited computing…

Injection of transient faults as a way to attack cryptographic implementations has been largely studied in the last decade. Several attacks that use electromagnetic fault injection against hardware or software architectures have already…

Deep learning as a service (DLaaS) has been intensively studied to facilitate the wider deployment of the emerging deep learning applications. However, DLaaS may compromise the privacy of both clients and cloud servers. Although some…

Safety filtering is an effective method for enforcing constraints in safety-critical systems, but existing methods typically assume perfect state information. This limitation is especially problematic for systems that rely on neural network…

The Lightning Network is a scaling solution for Bitcoin that promises to enable rapid and private payment processing. In Lightning, multi-hop payments are secured by utilizing Hashed Time-Locked Contracts (HTLCs) and encrypted on the…

Deep neural networks (DNNs) have become one of the enabling technologies in many safety-critical applications, e.g., autonomous driving and medical image analysis. DNN systems, however, suffer from various kinds of threats, such as…

Recent years have brought microarchitectural security intothe spotlight, proving that modern CPUs are vulnerable toseveral classes of microarchitectural attacks. These attacksbypass the basic isolation primitives provided by the…

Cloud applications expose - besides service endpoints - also potential or actual vulnerabilities. Therefore, cloud security engineering efforts focus on hardening the fortress walls but seldom assume that attacks may be successful. At least…

The growing computational demand for deep neural networks ( DNNs) has raised concerns about their energy consumption and carbon footprint, particularly as the size and complexity of the models continue to increase. To address these…

The increasing demand for on-device deep learning services calls for a highly efficient manner to deploy deep neural networks (DNNs) on mobile devices with limited capacity. The cloud-based solution is a promising approach to enabling deep…