Related papers: Noisy Neighbor: Exploiting RDMA for Resource Exhau…

Data-intensive workloads and applications, such as machine learning (ML), are fundamentally limited by traditional computing systems based on the von-Neumann architecture. As data movement operations and energy consumption become key…

Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety behavior remain poorly understood. We introduce the Attention Redistribution Attack (ARA),…

Recent neural networks (NNs) with self-attention exhibit competitiveness across different AI domains, but the essential attention mechanism brings massive computation and memory demands. To this end, various sparsity patterns are introduced…

Adversarial attacks have exposed serious vulnerabilities in Deep Neural Networks (DNNs) through their ability to force misclassifications through human-imperceptible perturbations to DNN inputs. We explore a new direction in the field of…

While neural machine translation (NMT) models achieve success in our daily lives, they show vulnerability to adversarial attacks. Despite being harmful, these attacks also offer benefits for interpreting and enhancing NMT models, thus…

Since local LLM inference on resource-constrained edge devices imposes a severe performance bottleneck, this paper proposes distributed prompt caching to enhance inference performance by cooperatively sharing intermediate processing states…

FPGAs have shown great potential in providing low-latency and energy-efficient solutions for deep neural network (DNN) inference applications. Currently, the majority of FPGA-based DNN accelerators in the cloud run in a time-division…

Frontier AI developers are relying on layers of safeguards to protect against catastrophic misuse of AI systems. Anthropic and OpenAI guard their latest Opus 4 model and GPT-5 models using such defense pipelines, and other frontier…

Automatic decision-making approaches, such as reinforcement learning (RL), have been applied to (partially) solve the resource allocation problem adaptively in the cloud computing system. However, a complete cloud resource allocation…

Neural image compression (NIC) has become the state-of-the-art for rate-distortion performance, yet its security vulnerabilities remain significantly less understood than those of classifiers. Existing adversarial attacks on NICs are often…

As an enhanced version of massive machine-type communication in 5G, massive communication has emerged as one of the six usage scenarios anticipated for 6G, owing to its potential in industrial internet-of-things and smart metering. Driven…

Mobile edge computing (MEC) has been envisaged as a promising technique in the next-generation wireless networks. In order to improve the security of computation tasks offloading and enhance user connectivity, physical layer security and…

Due to the recent developments in the field of full-duplex radios and cognitive radios, a new class of reactive jamming attacks has gained attention wherein an adversary transmits jamming energy over the victim's frequency band and also…

Recent increases in the computational demands of deep neural networks (DNNs), combined with the observation that most input samples require only simple models, have sparked interest in $input$-$adaptive$ multi-exit architectures, such as…

Cache-assisted ultra-dense mobile edge computing (MEC) networks are a promising solution for meeting the increasing demands of numerous Internet-of-Things mobile devices (IMDs). To address the complex interferences caused by small base…

Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial attacks, even in a black-box scenario. However, most of the existing black-box attack algorithms need to make a huge amount of queries to perform…

Existing black-box attacks on deep neural networks (DNNs) so far have largely focused on transferability, where an adversarial instance generated for a locally trained model can "transfer" to attack other learning models. In this paper, we…

Parallelization is featured by DNS recursive servers to do time-consuming recursions on behalf on clients. As common DNS configurations, recursive servers should allow a reasonable timeout for each recursion which may take as long as…

Stack-based memory corruption vulnerabilities have long been exploited by attackers to execute arbitrary code or perform unauthorized memory operations. Various defense mechanisms have been introduced to mitigate stack memory errors, but…

This paper focuses on evaluating the outage performance of a dual-hop single-phase non-orthogonal multiple-access (NOMA) system. The base station employs the Alamouti space-time block coding technique (Alamouti-STBC), enabling simultaneous…