Conventional fairness in multi-tenant Large Language Model (LLM) inference services is typically defined by system-centric metrics such as equitable resource allocation. We argue that this is unilateral and it creates a gap between measured system performance and actual user-perceived quality. We challenge this notion by introducing and formalizing Experiential Fairness, a user-centric paradigm that shifts the objective from equality of opportunity (resource access) to equity of outcome (user experience). With this motivation we propose ExFairS, a lightweight scheduling framework that perceives each user's satisfaction as a composite measure of Service Level Objective (SLO) compliance and resource consumption, and dynamically re-orders the serving queue guided by a credit-based priority mechanism. Extensive experiments on an 8-GPU NVIDIA V100 node show that ExFairS reduces the SLO violation rate by up to 100% and improves system throughput by 14-21.9%, outperforming state-of-the-art schedulers and delivering a demonstrably higher degree of Experiential Fairness.

Retrieval-Augmented Generation (RAG) expands the knowledge boundary of large language models (LLMs) at inference by retrieving external documents as context. However, retrieval becomes increasingly time-consuming as the knowledge databases grow in size. Existing acceleration strategies either compromise accuracy through approximate retrieval, or achieve marginal gains by reusing results of strictly identical queries. We propose HaS, a homology-aware speculative retrieval framework that performs low-latency speculative retrieval over restricted scopes to obtain candidate documents, followed by validating whether they contain the required knowledge. The validation, grounded in the homology relation between queries, is formulated as a homologous query re-identification task: once a previously observed query is identified as a homologous re-encounter of the incoming query, the draft is deemed acceptable, allowing the system to bypass slow full-database retrieval. Benefiting from the prevalence of homologous queries under real-world popularity patterns, HaS achieves substantial efficiency gains. Extensive experiments demonstrate that HaS reduces retrieval latency by 23.74% and 36.99% across datasets with only a 1-2% marginal accuracy drop. As a plug-and-play solution, HaS also significantly accelerates complex multi-hop queries in modern agentic RAG pipelines. Source code is available at: https://github.com/ErrEqualsNil/HaS.

Modern mobile apps widely embed WebView to enable rich and dynamic content, making it an increasingly attractive target for attackers. It is well known that insufficient or improper input validation on WebView-loaded URLs can compromise the entire app or even the underlying system. Among these threats, one of the most critical attack vectors is the DeepLink Attack, which often requires only a single user click to exploit WebView vulnerabilities. Despite the deployment of defense such as URL allowlists, misconfigurations and inconsistent implementations continue to expose apps to exploitation.In this paper, we present DeepExploitor, the first automated exploit generation framework targeting vulnerabilities exploitable via DeepLink Attack. DeepExploitor addresses two key challenges: First, it statically models complex, app-specific routing encapsulation and customized input parsing logic by extracing constraint-related code and resolving them through large language models (LLMs), enabling scalable discovery of valid exploits. Second, it identifies and mutates trusted domains embedded in the app to bypass black-box defenses such as domain-based allowlists. We evaluated DeepExploitor on 433 of the most popular Android apps and uncovered 83 zero-day vulnerabilities, including 24 rated as high or critical severity. All findings were responsibly disclosed to affected vendors, with 35 acknowledged to date or assigned CVE/CNVD identifiers.

LLMs offer a promising avenue to overcome the limitations of traditional taint analysis techniques, with a growing number of studies leveraging LLMs for taint analysis and its downstream applications. However, these studies lack a systematic understanding of LLMs’ taint analysis capabilities, limiting their transferability and reliability. To bridge this gap and better apply LLMs to static taint analysis, we aim to comprehensively measure and understand LLMs’ taint analysis capabilities.Using existing benchmarks is a straightforward approach, but they are unsuitable due to issues such as training data leakage, not accounting for LLMs’ features, and improper assessment criteria. Manually constructing new benchmarks is not only labor-intensive but also struggles to remain effective as LLMs evolve. To address these, we propose LLMCapLens, a dynamic benchmark generation framework to systematically measure and enhance LLMs’ capabilities. LLMCapLens models influencing factors of LLMs’ taint analysis capabilities, employing a Basic Unit-Based generation method and a lightweight dynamic taint analysis-based verification method to implement the automated generation of targeted benchmarks, ensuring both diversity and correctness. Furthermore, LLMCapLens proposes a measurement-driven, training-free, model-specific enhancement approach.We apply LLMCapLens to 10 mainstream LLMs, revealing how they perform under various influencing factors and identifying unique characteristics, such as the underlying error causes for each model. Notably, our enhancement approach significantly improves LLM performance—GPT-4 Turbo, for instance, achieved improvements across 16 out of 19 factors, with an average True Negative Rate increase of 21.29%. Finally, we validate the real-world impact of our method by applying enhanced LLMs to vulnerability detection, demonstrating a substantial improvement over prior approaches.

This paper introduces a novel spectrum resource sharing framework in Vehicle-to-Everything (V2X) communication networks based on multi-agent reinforcement learning with graph emergent communication (MARLGEC). We formulate resource sharing as a distributed multi-agent reinforcement learning (MARL) problem, where each vehicle acts as an agent, interacting with the environment to optimize spectrum allocation strategies. The introduction of the emergent communication mechanism enhances cooperation among agents in the distributed framework. Meanwhile, the graph attention mechanism effectively reduces the communication overhead incurred by emergent communication. This enables reliable vehicle-to-vehicle (V2V) payload transmission and improves system performance under varying network conditions. The experimental results validate the method’s effectiveness, demonstrating its ability to adapt to the dynamic environment and outperform existing MARL approaches that lack communication mechanisms.

This article presents a reference phase-shifting architecture (PSA) based on a phase-locked loop (PLL) and a digital-to-time converter (DTC). The double-path phase modulation scheme (DPMS) is proposed to accelerate the settling time of the reference PSA. Off-chip calibration is added to mitigate the effects of nonlinearity in the DPMS process. Additionally, a DTC with improved retiming is proposed to reduce phase-shifting errors. The reference PSA with the DPMS is designed and fabricated in a commercial 22-nm CMOS technology. It occupies 0.048-mm2 active area and 12.8-mW dc power consumption. It achieves a 360° phase tuning range with a resolution of 1.26° at 24.75 GHz. The rms and peak phase errors are 1.38° and 2.6°, respectively. With the proposed DPMS, the settling time of reference PSA is significantly reduced from more than$1~\mu $s to less than 10 ns. Moreover, the PLL with DTC features a phase noise of −112.1 dBc/Hz at 1-MHz offset from 24.75 GHz and a 79.7-fs jitter integrated from 10 kHz to 30 MHz with 250-MHz reference clock. The figure of merits (FoMs) of jitter versus power for the proposed PLL with and without DTC are −250.9 and −251.4 dB, respectively.

As a promising paradigm, edge computing enhances service provisioning by offloading tasks to powerful servers at the network edge. Meanwhile, Non-Orthogonal Multiple Access (NOMA) and renewable energy sources are increasingly adopted for spectral efficiency and carbon footprint reduction. However, these new techniques inevitably introduce reliability risks to the edge system generally because of i) imperfect Channel State Information (CSI), which can misguide offloading decisions and cause transmission outages, and ii) unstable renewable energy supply, which complicates device availability. To tackle these issues, we first establish a system model that measures service reliability based on probabilistic principles for the NOMA-based edge system. As a solution, a Reliable Offloading method with Multi-Agent deep reinforcement learning (ROMA) is proposed. In ROMA, we first reformulate the reliability-critical constraint into an long-term optimization problem via Lyapunov optimization. We discretize the hybrid action space and convert the resource allocation on edge servers into a 0-1 knapsack problem. The optimization problem is then formulated as a Partially Observable Markov Decision Process (POMDP) and addressed by multi-agent proximal policy optimization (PPO). Experimental evaluations demonstrate the superiority of ROMA over existing methods in reducing grid energy costs and enhancing system reliability, achieving Pareto-optimal performance under various settings.

In recent years, there have been numerous cyber security issues that have caused considerable damage to the society. The development of efficient and reliable Intrusion Detection Systems (IDSs) is an effective countermeasure against the growing cyber threats. In modern high-bandwidth, large-scale network environments, traditional IDSs suffer from a high rate of missed and false alarms. Researchers have introduced machine learning techniques into intrusion detection with good results. However, due to the scarcity of attack data, such methods’ training sets are usually unbalanced, affecting the analysis performance. In this paper, we survey and analyze the design principles and shortcomings of existing oversampling methods. Based on the findings, we take the perspective of imbalance and high dimensionality of datasets in the field of intrusion detection and propose an oversampling technique based on Generative Adversarial Networks (GAN) and feature selection. Specifically, we model the complex high-dimensional distribution of attacks based on Gradient Penalty Wasserstein GAN (WGAN-GP) to generate additional attack samples. We then select a subset of features representing the entire dataset based on analysis of variance, ultimately generating a rebalanced low-dimensional dataset for machine learning training. To evaluate the effectiveness of our proposal, we conducted experiments based on the NSL-KDD, UNSW-NB15, and CICIDS-2017 datasets. The experimental results show that our method can effectively improve the detection performance of machine learning models and outperform the baselines.

Hierarchical organization is widely used in high-radix routers to enable efficient scaling to higher switch port count. A general-purpose hierarchical router must be symmetrically designed with the same input buffer depth, resulting in a large amount of unused input buffers due to the different link lengths. Sharing input buffers between different input ports can improve buffer utilization, but the implementation overhead also increases with the number of shared ports. Previous work allowed input buffers to be shared among all router ports, which maximizes the buffer utilization but also introduces higher implementation complexity. Moreover, such design can impair performance when faced with long packets, due to the head-of-line blocking in intermediate buffers. In this work, we explain that sharing unused buffers between a subset of router ports is a more efficient design. Based on this observation, we propose Centralized Input Buffer Design in Hierarchical High-radix Routers (CIB-HIER), a novel centralized input buffer design for hierarchical high-radix routers. CIB-HIER integrates multiple input ports onto a single tile and organizes all unused input buffers in the tile as a centralized input buffer. CIB-HIER only allows the centralized input buffer to be shared between ports on the same tile, without introducing additional intermediate virtual channels or global scheduling circuits. Going beyond the basic design of CIB-HIER, the centralized input buffer can be used to relieve the head-of-line blocking caused by shallow intermediate buffers, by stashing long packets in the centralized input buffer. Experimental results show that CIB-HIER is highly effective and can significantly increase the throughput of high-radix routers.