Large language model (LLM) services increasingly rely on distributed inference across multiple GPU servers to sustain concurrent requests under limited compute, memory, and bandwidth resources. In such settings, a partitioned LLM can be represented as an inference chain (InFC), where the deployment decision determines both the sustainable concurrency ceiling (SCC) on the revenue side and the memory and communication overhead on the cost side. This paper studies the profit-aware inference chain deployment (InFCD) problem in heterogeneous data center networks. We show that increasing the InFC length does not monotonically improve profit: finer partitioning can relieve per-GPU resource bottlenecks and improve SCC, but may also increase deployment spread, inference path length, and internal traffic. To capture this tradeoff, we formulate profit-aware InFCD by jointly modeling static-weight vRAM occupation, per-user KV-cache occupation, user-side traffic, internal boundary traffic, and resource-coupled SCC, and prove its NP-hardness. We then propose the Maximum Sub-module Deployment Gain (MSDG) score and design an MSDG-based greedy algorithm. Theoretical analysis characterizes its online complexity and establishes a conditional positive-profit preservation property. Simulations show that MSDG improves total profit over SCC-oriented, cost-oriented, and local-profit-oriented baselines, characterize empirical optimality gaps and SLO sensitivity.

Large vision-language models (LVLMs) derive their capabilities from extensive training on vast corpora of visual and textual data. Empowered by large-scale parameters, these models often exhibit strong memorization of their training data, rendering them susceptible to membership inference attacks (MIAs). Existing MIA methods for LVLMs typically operate under white- or gray-box assumptions, by extracting likelihood-based features for the suspected data samples based on the target LVLMs. However, mainstream LVLMs generally only expose generated outputs while concealing internal computational features during inference, limiting the applicability of these methods. In this work, we propose the first black-box MIA framework for LVLMs, based on a prior knowledge-calibrated memory probing mechanism. The core idea is to assess the model memorization of the private semantic information embedded within the suspected image data, which is unlikely to be inferred from general world knowledge alone. We conducted extensive experiments across four LVLMs and three datasets. Empirical results demonstrate that our method effectively identifies training data of LVLMs in a purely black-box setting and even achieves performance comparable to gray-box and white-box methods. Further analysis reveals the robustness of our method against potential adversarial manipulations, and the effectiveness of the methodology designs. Our code and data are available at \url{https://github.com/spmede/KCMP}.

The rapid growth of Low Earth Orbit (LEO) satellites, particularly with the increasing deployment of intelligent computing capabilities using commercial off-the-shelf (COTS) hardware, presents significant opportunities to enhance the quality of in-orbit services. However, the current onboard conditions remain insufficient to enhance model accuracy by increasing model size, and inadequate accuracy hampers the effectiveness of in-orbit services. The satellite-ground federated learning (FL) paradigm, leveraging collaborative fine-tuning, offers a promising solution to continuously improve onboard model performance. Prior studies have focused on optimizing fine-tuning under constraints like limited bandwidth and computational resources, they often overlook two critical challenges: the scarcity and skewness of labeled onboard data and the long revisit cycles of satellites. To address these challenges and better support in-orbit services, this paper designs a realistic simulation methodology for the onboard fine-tuning process and conducts a comprehensive measurement study. Based on insights from the measurement results, we propose an efficient satellite-ground federated fine-tuning system,FedCLR+. In this system, we design a FedCLR algorithm to enhance system accuracy through representation optimization. Additionally, we propose a hybrid bias-compensated strategy to further mitigate accuracy loss by enriching the diversity of aggregation information. Experimental results show thatFedCLR+significantly enhances accuracy by up to 21.61×, reduces transmission volume by an average of 7.29%, and maintaining acceptable additional overhead compared to baselines.

In the current AI era, mobile devices such as smartphones are tasked with executing a myriad of deep neural networks (DNNs) locally. It presents a complex landscape, as these models are highly fragmented in terms of architecture, operators, and implementations. Such fragmentation poses significant challenges to the co-optimization of hardware, systems, and algorithms for efficient and scalable mobile AI.

Large constellations of Low Earth Orbit (LEO) satellites have been launched for Earth observation and satellite-ground communication, which collect massive imagery and sensor data. These data can enhance the AI capabilities of satellites to address global challenges such as real-time disaster navigation and mitigation. Prior studies proposed leveraging federated learning (FL) across satellite-ground to collaboratively train a share machine learning (ML) model in a privacy-preserving mechanism. However, they mostly focus on single unique challenges such as limited ground-to-satellite bandwidth, short connection window, and long connection cycle, while ignoring the completeness of these challenges in deploying efficient FL frameworks in space. In this paper, we propose an efficient satellite-ground FL framework, SatelliteFL, to address these three challenges collectively. Its key idea is to ensure that each satellite must complete per-round training within each connection window. Moreover, we design a progressive block-wise quantization algorithm that determines a unique bitwidth for each block of the ML model to maximize the model utility while not exceeding the connection window. We evaluate SatelliteFL by plugging an implemented FL platform into real-world satellite networks and satellite images. The results show that SatelliteFL highly accelerates the convergence by up to 2.8× and improves the bandwidth utilization ratio by up to 9.3× compared to the state-of-the-art methods.

The rapid development of Low Earth Orbit (LEO) satellite constellations offers significant potential for in-orbit services, particularly in mitigating the impact of sudden natural disasters. However, the massive data collected by these satellites are often large and severely constrained by limited transmission capabilities when sending data to the ground. Satellite computing, which utilizes onboard computational capacity to process data before transmission, presents a promising solution to alleviate the downlink burden. Nonetheless, this paradigm introduces another bottleneck: limited onboard computing capacity, resulting in slow in-orbit processing and poor results. Current satellite computing systems struggle to efficiently address both data transmission and computing bottlenecks, particularly for urgent disaster services that demand accurate and timely results. Thus, we introduce an efficient satellite computing system designed to jointly mitigate these bottlenecks, thereby providing better service. The core idea is to utilize onboard computing capacity for swift in-orbit annotation of image regions, enabling adaptive compression and download based on annotation confidence and perceived downlink availability. Once the data is downloaded, image restoration and re-inference are performed on the ground to enhance accuracy. Compared to satellite-only inference, our system demonstrates an average improvement in inference accuracy of 3.8%. Furthermore, compared to ground-only inference, with only a 2.8% accuracy loss, our system achieves a 38.4% reduction in response time and saves 71.6% of downlink volume on average.

Federated learning (FL) has emerged as a prominent paradigm enabling collaborative model training without transmitting local data, thereby safeguarding data privacy. However, the practical implementation of FL systems on these devices faces a significant challenge: the heterogeneous corruption of data on individual clients, leading to unanticipated accuracy degradation during real-world deployment. In this work, we first introduce a realistic data corruption simulation framework to test the robustness of FL systems. In this framework, an in-depth analysis of potential data corruption patterns occurring on devices is conducted, followed by the construction of individual datasets with varying corruption types and degrees. Such data corruption results in the robustness degradation of conventional FL protocol (FedAVG) significantly higher than centralized learning (CL). Atop this key observation, we propose an adaptive FL protocol that emulates the CL training process. The protocol leverages imbalanced client data sampling to mitigate the negative impact of data corruption. Furthermore, a hybrid aggregation strategy is designed to accelerate model convergence and reduce additional communication overhead. Extensive experiments validate the effectiveness of our approach in enhancing the robustness of FL systems against client data corruption, which achieves up to 12% higher converge accuracy than FedAVG-based systems with acceptable overhead.