Recently, there has been a surge in the development of advanced intelligent generative content (AIGC), especially large language models (LLMs). For many downstream tasks, it is necessary to fine-tune LLMs using private data. While federated learning offers a promising privacy-preserving solution to LLM fine-tuning, the substantial size of an LLM, combined with high computational and communication demands, makes it hard to apply to handle downstream tasks. More importantly, private edge servers often possess varying computing and network resources in real-world scenarios, introducing additional complexities to LLM fine-tuning. To tackle these problems, we design and implement an automated federated pipeline, named, to fine-tune LLMs on heterogeneous edge servers with minimal training cost and no additional inference latency. firstly identifies the weights to be fine-tuned based on their contributions to the LLM training. It then configures a low-rank adapter for each selected weight within the resource constraints of the edge server and aggregates these local adapters from all edge servers to fine-tune the whole LLM. Finally, it appropriately quantizes the parameters of LLM to reduce memory consumption according to the requirements of edge servers. Extensive experiments demonstrate that expedites model training and achieves higher accuracy than the state-of-the-art benchmarks.

Recently, the increasing deployment of LEO satellite systems has enabled various space analytics (e.g., crop and climate monitoring), which heavily relies on the advancements in deep learning (DL). However, the intermittent connectivity between LEO satellites and ground station (GS) significantly hinders the timely transmission of raw data to GS for centralized learning, while the scaled-up DL models hamper distributed learning on resource-constrained LEO satellites. Thoughsplit learning(SL) can be a potential solution to these problems by partitioning a model and offloading primary training workload to GS, the labor-intensive labeling process remains an obstacle, with intermittent connectivity and data heterogeneity being other challenges. In this paper, we propose LEO-Split, asemi-supervised(SS) SL design tailored for satellite networks to combat these challenges. Leveraging SS learning to handle (labeled) data scarcity, we construct an auxiliary model to tackle the training failure of the satellite-GS non-contact time. Moreover, we propose a pseudo-labeling algorithm to rectify data imbalances across satellites. Lastly, an adaptive activation interpolation scheme is devised to prevent the overfitting of server-side sub-model training at GS. Extensive experiments with real-world LEO satellite traces (e.g., Starlink) demonstrate that our LEO-Split framework achieves superior performance compared to state-of-the-art benchmarks.

Recently, deep reinforcement learning (DRL) has emerged as a promising approach for robotic control. However, the deployment of DRL in real-world robots is hindered by its sensitivity to environmental perturbations. While existing whitebox adversarial attacks rely on local gradient information and apply uniform perturbations across all states to evaluate DRL robustness, they fail to account for temporal dynamics and statespecific vulnerabilities. To combat the above challenge, we first conduct a theoretical analysis of white-box attacks in DRL by establishing the adversarial victim-dynamics Markov decision process (AVD-MDP), to derive the necessary and sufficient conditions for a successful attack. Based on this, we propose a selective state-aware reinforcement adversarial attack method, named STAR, to optimize perturbation stealthiness and state visitation dispersion. STAR first employs a soft mask-based state-targeting mechanism to minimize redundant perturbations, enhancing stealthiness and attack effectiveness. Then, it incorporates an information-theoretic optimization objective to maximize mutual information between perturbations, environmental states, and victim actions, ensuring a dispersed state-visitation distribution that steers the victim agent into vulnerable states for maximum return reduction. Extensive experiments demonstrate that STAR outperforms state-of-the-art benchmarks

Large language models (LLMs) have achieved remarkable success in various tasks, such as decision-making, reasoning, and question answering. They have been widely used in edge devices. However, fine-tuning LLMs to specific tasks at the edge is challenging due to the high computational cost and the limited storage and energy resources at the edge. To address this issue, we propose TaskEdge, a task-aware parameter-efficient fine-tuning framework at the edge, which allocates the most effective parameters to the target task and only updates the task-specific parameters. Specifically, we first design a parameter importance calculation criterion that incorporates both weights and input activations into the computation of weight importance. Then, we propose a model-agnostic task-specific parameter allocation algorithm to ensure that task-specific parameters are distributed evenly across the model, rather than being concentrated in specific regions. In doing so, TaskEdge can significantly reduce the computational cost and memory usage while maintaining performance on the target downstream tasks by updating less than 0.1% of the parameters. In addition, TaskEdge can be easily integrated with structured sparsity to enable acceleration by NVIDIA’s specialized sparse tensor cores, and it can be seamlessly integrated with LoRA to enable efficient sparse low-rank adaptation. Extensive experiments on various tasks demonstrate the effectiveness of TaskEdge.

Deep neural networks (DNNs) are vulnerable to adversarial examples, in which DNNs are misled to false outputs due to inputs containing imperceptible perturbations. Adversarial training, a reliable and effective method of defense, may significantly reduce the vulnerability of neural networks and becomes the de facto standard for robust learning. While many recent works practice the data-centric philosophy, such as how to generate better adversarial examples or use generative models to produce additional training data, we look back to the models themselves and revisit the adversarial robustness from the perspective of deep feature distribution as an insightful complementarity. In this paper, we propose Branch Orthogonality adveRsarial Training (BORT) to obtain state-of-the-art performance with solely the original dataset for adversarial training. To practice our design idea of integrating multiple orthogonal solution spaces, we leverage a simple multi-branch neural network and propose a corresponding loss function, branch-orthogonal loss, to make each solution space of the multi-branch model orthogonal. We evaluate our approach on CIFAR-10, CIFAR-100 and SVHN against$\ell_{\infty}$norm-bounded perturbations of size$\epsilon=8 / 255$, respectively. Exhaustive experiments are conducted to show that our method goes beyond all state-of-the-art methods without any tricks. Compared to all methods that do not use additional data for training, our models achieve 67.3 % and 41.5 % robust accuracy on CIFAR-10 and CIFAR-100 (improving upon the state-of-the-art by$\mathbf{+7.23 \%}$and$\mathbf{+9.07 \%}$).

Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its real-world deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adversarial attack methods, adapted from supervised learning, fail to effectively target DRL agents as they overlook temporal dynamics and indiscriminately perturb all state dimensions, limiting their impact on long-term rewards. To address these challenges, we propose the Adaptive Gradient-Masked Reinforcement (AGMR) Attack, a white-box attack method that combines DRL with a gradient-based soft masking mechanism to dynamically identify critical state dimensions and optimize adversarial policies. AGMR selectively allocates perturbations to the most impactful state features and incorporates a dynamic adjustment mechanism to balance exploration and exploitation during training. Extensive experiments demonstrate that AGMR outperforms state-of-the-art adversarial attack methods in degrading the performance of the victim agent and enhances the victim agent’s robustness through adversarial defense mechanisms.

Ramp merging is one of the bottlenecks in traffic systems, which commonly cause traffic congestion, accidents, and severe carbon emissions. In order to address this essential issue and enhance the safety and efficiency of connected and autonomous vehicles (CAVs) at multi-lane merging zones, we propose a novel collaborative decision-making framework, namedAgentsCoMerge, to leverage large language models (LLMs). Specifically, we first design a scene observation and understanding module to allow an agent to capture the traffic environment. Then we propose a hierarchical planning module to enable the agent to make decisions and plan trajectories based on the observation and the agent's own state. In addition, in order to facilitate collaboration among multiple agents, we introduce a communication module to enable the surrounding agents to exchange necessary information and coordinate their actions. Finally, we develop a reinforcement reflection guided training paradigm to further enhance the decision-making capability of the framework. Extensive experiments are conducted to evaluate the performance of our proposed method, demonstrating its superior efficiency and effectiveness for multi-agent collaborative decision-making under various ramp merging scenarios.

Recently, a large number of Low Earth Orbit (LEO) satellites have been launched and deployed successfully in space. Due to multimodal sensors equipped by the LEO satellites, they serve not only for communications but also for various machine learning applications. However, a ground station (GS) may be incapable of downloading such a large volume of raw sensing data for centralized model training due to the limited contact time with LEO satellites (e.g. 5 minutes). Therefore,federated learning(FL) has emerged as the promising solution to address this problem via on-device training. Unfortunately, enabling FL on LEO satellites still face three critical challenges: i) heterogeneous computing and memory capabilities, ii) limited downlink/uplink rate, and iii) model staleness. To this end, we proposeFedSNas a general FL framework to tackle the above challenges. Specifically, we first present a novel sub-structure scheme to enable heterogeneous local model training considering different computing, memory, and communication constraints on LEO satellites. Additionally, we propose a pseudo-synchronous model aggregation strategy to dynamically schedule model aggregation for compensating model staleness. Extensive experiments with real-world satellite data demonstrate that FedSN framework achieves higher accuracy, lower computing, and communication overhead than the state-of-the-art benchmarks.

Due to sophisticated deployments of all kinds of wireless networks (e.g., 5G, Wi-Fi, Bluetooth, LEO satellite, etc.), multiband signals distribute in a large bandwidth (e.g., from 70 MHz to 8 GHz). Consequently, for network monitoring and spectrum sharing applications, a sniffer for extracting physical layer information, such as structure of packet, with low sampling rate (especially, sub-Nyquist sampling) can significantly improve their cost- and energy-efficiency. However, to achieve a multiband signals sniffer is really a challenge. To this end, we propose Sums, a system that can sniff and analyze multiband signals in a blind manner. Our Sums takes advantage of hardware and algorithm co-design, multi-coset sub-Nyquist sampling hardware, and a multi-task deep learning framework. The hardware component breaks the Nyquist rule to sample GHz bandwidth, but only pays for a 50 MSPS sampling rate. Our multi-task learning framework directly tackles the sampling data to perform spectrum sensing, physical layer protocol recognition, and demodulation for deep inspection from multiband signals. Extensive experiments demonstrate that Sums achieves higher accuracy than the state-of-the-art baselines in spectrum sensing, modulation classification, and demodulation. As a result, our Sums can help researchers and end-users to diagnose or troubleshoot their problems of wireless infrastructures deployments in practice.