Related papers: PiPoMonitor: Mitigating Cross-core Cache Attacks U…

Deep learning models are widely employed in safety-critical applications yet remain susceptible to adversarial attacks -- imperceptible perturbations that can significantly degrade model performance. Conventional defense mechanisms…

Hateful meme detection aims to prevent the proliferation of hateful memes on various social media platforms. Considering its impact on social environments, this paper introduces a previously ignored but significant threat to hateful meme…

Compression algorithms are widely used as they save memory without losing data. However, elimination of redundant symbols and sequences in data leads to a compression side channel. So far, compression attacks have only focused on the…

Collective operations are cornerstones of both HPC applications and large-scale AI training and inference, yet benchmarking them in a systematic and reproducible way remains difficult on modern systems due to the complexity of their…

Unsafe memory accesses in programs written using popular programming languages like C/C++ have been among the leading causes for software vulnerability. Prior memory safety checkers such as SoftBound enforce memory spatial safety by…

With the improvements of computing technology, more and more applications embed powerful ARM processors into their devices. These systems can be attacked by redirecting the control-flow of a program to bypass critical pieces of code such as…

Kubernetes (K8s) is widely used to orchestrate containerized applications, including critical services in domains such as finance, healthcare, and government. However, its extensive and feature-rich API interface exposes a broad attack…

Deep neural networks are vulnerable to adversarial examples, which dramatically alter model output using small input changes. We propose Neural Fingerprinting, a simple, yet effective method to detect adversarial examples by verifying…

With transistor scaling reaching its limits, interposer-based integration of dies (chiplets) is gaining traction. Such an interposer-based integration enables finer and tighter interconnect pitch than traditional system-on-packages and…

This paper outlines a cyber-physical authentication strategy to protect power system infrastructure against false data injection (FDI) attacks. We demonstrate that it is feasible to use small, low-cost, yet highly attack-resistant security…

Micro-architectural attacks use information leaked through shared resources to break hardware-enforced isolation. These attacks have been used to steal private information ranging from cryptographic keys to privileged Operating System (OS)…

We introduce 2DIO, a microbenchmark creating cache-accurate, stressful I/O traces. While existing tools are limited to generating traces with well-behaved, concave hit ratio curves, 2DIO produces ones with tunable complex cache behaviors,…

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing…

Recent discovery of security attacks in advanced processors, known as Spectre and Meltdown, has resulted in high public alertness about security of hardware. The root cause of these attacks is information leakage across "covert channels"…

In multi-hop wireless systems, the need for cooperation among nodes to relay each other's packets exposes them to a wide range of security attacks. A particularly devastating attack is the wormhole attack, where a malicious node records…

Contrast pattern mining (CPM) aims to discover patterns whose support increases significantly from a background dataset compared to a target dataset. CPM is particularly useful for characterising changes in evolving systems, e.g., in…

Rapid adoption of AI technologies raises several major security concerns, including the risks of adversarial perturbations, which threaten the confidentiality and integrity of AI applications. Protecting AI hardware from misuse and diverse…

Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Although evolving defense mechanisms can detect most existing…

With increasingly sophisticated cyber-adversaries able to access a wider repertoire of mechanisms to implant malware such as ransomware, CPU/GPU keyloggers, and stealthy kernel rootkits, there is an urgent need for techniques to detect and…

Text-to-image diffusion models achieve high-fidelity image generation from natural language prompts. ControlNets extend these models by enabling conditioning on structural inputs (e.g., edge maps, depth, pose), providing fine-grained…