papers

Publications (57)

cs.LG2026

Jailbreak-as-a-Service++: Unveiling Distributed AI-Driven Malicious Information Campaigns Powered by LLM Crowdsourcing

Yu Yan, Sheng Sun, Mingfeng Li +6

To prevent the misuse of Large Language Models (LLMs) for malicious purposes, numerous efforts have been made to develop the safety alignment mechanisms of LLMs. However, as multip…

cs.CR2022

Towards 5G Zero Trusted Air Interface Architecture

Sheng Sun, Morris Repeta, Mike Healy +3

5G is destined to be supporting large deployment of Industrial IoT (IIoT) with the characteristics of ultra-high densification and low latency. 5G utilizes a more intelligent archi…

cs.RO2025

TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving

Xuefeng Jiang, Yuan Ma, Pengxiang Li +7

In recent years, diffusion models have demonstrated remarkable potential across diverse domains, from vision generation to language modeling. Transferring its generative capabiliti…

cs.DC2025

Learnable Sparse Customization in Heterogeneous Edge Computing

Jingjing Xue, Sheng Sun, Min Liu +3

To effectively manage and utilize massive distributed data at the network edge, Federated Learning (FL) has emerged as a promising edge computing paradigm across data silos. Howeve…

physics.app-ph2023

Non-iterative Methods in Inhomogeneous Background Inverse Scattering Imaging Problem Assisted by Swin Transformer Network

Naike Du, Tiantian Yin, Jing Wang +5

A deep learning-assisted inversion method is proposed to solve the inhomogeneous background imaging problem. Three non-iterative methods, namely the distorted-Born (DB) major curre…

cs.LG2022

Towards Federated Learning against Noisy Labels via Local Self-Regularization

Xuefeng Jiang, Sheng Sun, Yuwei Wang +1

Federated learning (FL) aims to learn joint knowledge from a large scale of decentralized devices with labeled data in a privacy-preserving manner. However, since high-quality labe…

cs.LG2026

GDformer: Going Beyond Subsequence Isolation for Multivariate Time Series Anomaly Detection

Qingxiang Liu, Xiaoliang Luo, Chenghao Liu +5

Unsupervised anomaly detection of multivariate time series is a challenging task, given the requirements of deriving a compact detection criterion without accessing the anomaly poi…

cs.LG2024

Logits Poisoning Attack in Federated Distillation

Yuhan Tang, Zhiyuan Wu, Bo Gao +3

Federated Distillation (FD) is a novel and promising distributed machine learning paradigm, where knowledge distillation is leveraged to facilitate a more efficient and flexible cr…

cs.CV2026

FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Models

Wei Li, Peijin Jia, Yuan Ma +9

FoMoVLA enhances vision-language-action models by jointly predicting future visual features and tracking sparse 2D points, providing both goal states and motion paths to improve co…

#vision-language-action#visual foresight#motion guidance#sparse point tracking
cs.LG2025

Privacy-Enhanced Training-as-a-Service for On-Device Intelligence: Concept, Architectural Scheme, and Open Problems

Zhiyuan Wu, Sheng Sun, Yuwei Wang +4

On-device intelligence (ODI) enables artificial intelligence (AI) applications to run on end devices, providing real-time and customized AI inference without relying on remote serv…

cs.IT2024

Breaking the Degrees-of-Freedom Limit of Holographic MIMO Communications: A 3-D Antenna Array Topology

Shuai S. A. Yuan, Jie Wu, Hongjing Xu +9

The performance of holographic multiple-input multiple-output (MIMO) communications, employing two-dimensional (2-D) planar antenna arrays, is typically compromised by finite degre…

cs.LG2024

Personalized Federated Learning for Spatio-Temporal Forecasting: A Dual Semantic Alignment-Based Contrastive Approach

Qingxiang Liu, Sheng Sun, Yuxuan Liang +2

The existing federated learning (FL) methods for spatio-temporal forecasting fail to capture the inherent spatio-temporal heterogeneity, which calls for personalized FL (PFL) metho…

cs.CR2026

Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks

Yu Yan, Sheng Sun, Shengjia Cheng +3

Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream…

physics.app-ph2022

Approaching the Fundamental Limit of Orbital Angular Momentum Multiplexing Through a Hologram Metasurface

Shuai S. A. Yuan, Jie Wu, Menglin L. N. Chen +9

Establishing and approaching the fundamental limit of orbital angular momentum (OAM) multiplexing are necessary and increasingly urgent for current multiple-input multiple-output r…

cs.CL2025

Collaborative Stance Detection via Small-Large Language Model Consistency Verification

Yu Yan, Sheng Sun, Zixiang Tang +2

Stance detection on social media aims to identify attitudes expressed in tweets towards specific targets. Current studies prioritize Large Language Models (LLMs) over Small Languag…

cs.LG2024

Federated Class-Incremental Learning with New-Class Augmented Self-Distillation

Zhiyuan Wu, Tianliu He, Sheng Sun +4

Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data. Mainstream FL methodologies overlook the dynamic nature…

cs.CV2026

Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise

Zibin Geng, Xuefeng Jiang, Jia Li +6

Prompt learning is a parameter-efficient approach for vision-language models, yet its robustness under label noise is less investigated. Visual content contains richer and more rel…

cs.CV2025

FNBench: Benchmarking Robust Federated Learning against Noisy Labels

Xuefeng Jiang, Jia Li, Nannan Wu +7

Robustness to label noise within data is a significant challenge in federated learning (FL). From the data-centric perspective, the data quality of distributed datasets can not be…

cs.LG2024

FedCache 2.0: Federated Edge Learning with Knowledge Caching and Dataset Distillation

Quyang Pan, Sheng Sun, Zhiyuan Wu +4

Federated Edge Learning (FEL) has emerged as a promising approach for enabling edge devices to collaboratively train machine learning models while preserving data privacy. Despite…

cs.LG2024

Knowledge Distillation in Federated Edge Learning: A Survey

Zhiyuan Wu, Sheng Sun, Yuwei Wang +4

The increasing demand for intelligent services and privacy protection of mobile and Internet of Things (IoT) devices motivates the wide application of Federated Edge Learning (FEL)…

cs.CR2025

Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs

Yu Yan, Sheng Sun, Zhe Wang +6

With the development of Large Language Models (LLMs), numerous efforts have revealed their vulnerabilities to jailbreak attacks. Although these studies have driven the progress in…

cs.LG2025

Robust Federated Learning against Noisy Clients via Masked Optimization

Xuefeng Jiang, Tian Wen, Zhiqin Yang +5

In recent years, federated learning (FL) has made significant advance in privacy-sensitive applications. However, it can be hard to ensure that FL participants provide well-annotat…

cs.LG2023

Improving Communication Efficiency of Federated Distillation via Accumulating Local Updates

Zhiyuan Wu, Sheng Sun, Yuwei Wang +3

As an emerging federated learning paradigm, federated distillation enables communication-efficient model training by transmitting only small-scale knowledge during the learning pro…

cs.MA2023

Resource-aware Probability-based Collaborative Odor Source Localization Using Multiple UAVs

Shan Wang, Sheng Sun, Min Liu +2

Benefitting from UAVs' characteristics of flexible deployment and controllable movement in 3D space, odor source localization with multiple UAVs has been a hot research area in rec…

eess.IV2024

Weakly-supervised land classification for coastal zone based on deep convolutional neural networks by incorporating dual-polarimetric characteristics into training dataset

Sheng Sun, Armando Marino, Wenze Shui +1

In this work we explore the performance of DCNNs on semantic segmentation using spaceborne polarimetric synthetic aperture radar (PolSAR) datasets. The semantic segmentation task u…

cs.CR2026

Composable Attestation: A Generalized Framework for Continuous and Incremental Trust in AI-Driven Distributed Systems

Sheng Sun, Sarah Evans

This paper presents composable attestation as a generalized cryptographic framework for Continuous and Incremental Trust in Distributed Systems,such as Artificial Intelligence (AI)…

cs.LG2024

Tackling Noisy Clients in Federated Learning with End-to-end Label Correction

Xuefeng Jiang, Sheng Sun, Jia Li +6

Recently, federated learning (FL) has achieved wide successes for diverse privacy-sensitive applications without sacrificing the sensitive private information of clients. However,…

cs.LG2023

Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation

Zhiyuan Wu, Sheng Sun, Yuwei Wang +5

Federated learning (FL) is a privacy-preserving machine learning paradigm in which the server periodically aggregates local model parameters from clients without assembling their p…

cs.IT2022

Electromagnetic Effective-Degree-of-Freedom Limit of a MIMO System in 2-D Inhomogeneous Environment

Shuai S. A. Yuan, Zi He, Sheng Sun +3

Compared with a single-input-single-output (SISO) wireless communication system, the benefit of multiple-input-multiple-output (MIMO) technology originates from its extra degree of…

cs.DC2023

FedBIAD: Communication-Efficient and Accuracy-Guaranteed Federated Learning with Bayesian Inference-Based Adaptive Dropout

Jingjing Xue, Min Liu, Sheng Sun +3

Federated Learning (FL) emerges as a distributed machine learning paradigm without end-user data transmission, effectively avoiding privacy leakage. Participating devices in FL are…

cs.AI2026

Rationale-Grounded In-Context Learning for Time Series Reasoning with Multimodal Large Language Models

Qingxiang Liu, Zhiqing Cui, Xiaoliang Luo +7

The underperformance of existing multimodal large language models for time series reasoning lies in the absence of rationale priors that connect temporal observations to their down…

cond-mat.mtrl-sci2024

The role of lattice thermal conductivity suppression by dopants from a holistic perspective

Shengnan Dai, Shijie Zhang, Ye Sheng +6

Dopants play an important role in improving electrical and thermal transport. In the traditional perspective, a dopant suppresses lattice thermal conductivity kL by adding point de…

cs.RO2025

The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning

Titong Jiang, Xuefeng Jiang, Yuan Ma +7

We present LightVLA, a simple yet effective differentiable token pruning framework for vision-language-action (VLA) models. While VLA models have shown impressive capability in exe…

cs.CR2021

zk-Fabric, a Polylithic Syntax Zero Knowledge Joint Proof System

Sheng Sun, Tong Wen

In this paper, we create a single-use and full syntax zero-knowledge proof system, a.k.a zk-Fabric. Comparing with zk-SNARKS and another variant zero-knowledge proofing system, zkB…

physics.app-ph2019

Ultra-wideband Reflection-type Metasurface for Generating Integer and Fractional Orbital Angular Momentum

Ling-Jun Yang, Sheng Sun, Wei E. I. Sha

Vortex beams carrying orbital angular momentum are extensively studied owing to its potential to expand channel capacity of microwave and optical communication. By utilizing the Pa…

physics.ins-det2014

Design of Wideband Microstrip Filters with Non-Equiripple Responses and Low Sensitivity

S. S. Gao, Sheng Sun

This paper presents a novel design procedure for wideband microstrip bandpass filters with non-equiripple filtering frequency responses and low sensitivity. Different from the trad…

cond-mat.mtrl-sci2023

Unraveling the Complexity of Metal Ion Dissolution: Insights from Hybrid First-Principles/Continuum Calculations

Mingqing Liu, Tong-Yi Zhang, Sheng Sun

The study of ion dissolution from metal surfaces has a long-standing history, wherein the gradual dissolution of solute atoms with increasing electrode potential, leading to their…

cs.DC2024

Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaboration

Zhiyuan Wu, Sheng Sun, Yuwei Wang +5

Federated Learning (FL) enables training Artificial Intelligence (AI) models over end devices without compromising their privacy. As computing tasks are increasingly performed by a…

cs.CL2026

SearchAttack: Red-Teaming LLMs against Knowledge-to-Action Threats under Online Web Search

Yu Yan, Sheng Sun, Mingfeng Li +6

Recently, people have suffered from LLM hallucination and have become increasingly aware of the reliability gap of LLMs in open and knowledge-intensive tasks. As a result, they hav…

physics.app-ph2021

Manipulation of Orbital Angular Momentum Spectrum Using Shape-Tailored Metasurfaces

Ling-Jun Yang, Sheng Sun, Wei E. I. Sha

Vortex beams carrying orbital angular momentum (OAM) have been widely applied in various electromagnetic, optical, and quantum systems. A tailored OAM spectrum composed of several…

cs.LG2026

Discrete Prototypical Memories for Federated Time Series Foundation Models

Liwei Deng, Qingxiang Liu, Xinhe Niu +5

Leveraging Large Language Models (LLMs) as federated learning (FL)-based time series foundation models offers a promising way to transfer the generalization capabilities of LLMs to…

cs.DC2025

Recursive Offloading for LLM Serving in Multi-tier Networks

Zhiyuan Wu, Sheng Sun, Yuwei Wang +5

Heterogeneous device-edge-cloud computing infrastructures have become widely adopted in telecommunication operators and Wide Area Networks (WANs), offering multi-tier computational…

cs.LG2024

Peak-Controlled Logits Poisoning Attack in Federated Distillation

Yuhan Tang, Aoxu Zhang, Zhiyuan Wu +4

Federated Distillation (FD) offers an innovative approach to distributed machine learning, leveraging knowledge distillation for efficient and flexible cross-device knowledge trans…

cs.CL2026

ZoFia: Zero-Shot Fake News Detection with Entity-Guided Retrieval and Multi-LLM Interaction

Lvhua Wu, Xuefeng Jiang, Sheng Sun +4

The rapid spread of fake news threatens social stability and public trust, highlighting the urgent need for its effective detection. Although large language models (LLMs) show pote…

cs.LG2025

FedICT: Federated Multi-task Distillation for Multi-access Edge Computing

Zhiyuan Wu, Sheng Sun, Yuwei Wang +4

The growing interest in intelligent services and privacy protection for mobile devices has given rise to the widespread application of federated learning in Multi-access Edge Compu…

cs.CL2026

from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors

Yu Yan, Sheng Sun, Zenghao Duan +5

Current studies have exposed the risk of Large Language Models (LLMs) generating harmful content by jailbreak attacks. However, they overlook that the direct generation of harmful…

cs.CL2025

Na'vi or Knave: Jailbreaking Language Models via Metaphorical Avatars

Yu Yan, Sheng Sun, Junqi Tong +2

Metaphor serves as an implicit approach to convey information, while enabling the generalized comprehension of complex subjects. However, metaphor can potentially be exploited to b…

cs.LG2024

REFOL: Resource-Efficient Federated Online Learning for Traffic Flow Forecasting

Qingxiang Liu, Sheng Sun, Yuxuan Liang +6

Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of r…

cs.DC2023

FedTrip: A Resource-Efficient Federated Learning Method with Triplet Regularization

Xujing Li, Min Liu, Sheng Sun +3

In the federated learning scenario, geographically distributed clients collaboratively train a global model. Data heterogeneity among clients significantly results in inconsistent…

cs.DC2024

FedCache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligence

Zhiyuan Wu, Sheng Sun, Yuwei Wang +6

Edge Intelligence (EI) allows Artificial Intelligence (AI) applications to run at the edge, where data analysis and decision-making can be performed in real-time and close to data…

cs.CR2025

SVAFD: A Secure and Verifiable Co-Aggregation Protocol for Federated Distillation

Tian Wen, Sheng Sun, Yuwei Wang +4

Secure Aggregation (SA) is an indispensable component of Federated Learning (FL) that concentrates on privacy preservation while allowing for robust aggregation. However, most SA d…

cs.DC2025

Beyond Model Scale Limits: End-Edge-Cloud Federated Learning with Self-Rectified Knowledge Agglomeration

Zhiyuan Wu, Sheng Sun, Yuwei Wang +5

The rise of End-Edge-Cloud Collaboration (EECC) offers a promising paradigm for Artificial Intelligence (AI) model training across end devices, edge servers, and cloud data centers…

physics.optics2024

Spin and Orbital Angular Momenta of Electromagnetic Waves: From Classical to Quantum Forms

Wei E. I. Sha, Zhihao Lan, Menglin L. N. Chen +2

Angular momenta of electromagnetic waves are important both in concepts and applications. In this work, we systematically discuss two types of angular momenta, i.e., spin angular m…

cs.LG2023

Federated Skewed Label Learning with Logits Fusion

Yuwei Wang, Runhan Li, Hao Tan +5

Federated learning (FL) aims to collaboratively train a shared model across multiple clients without transmitting their local data. Data heterogeneity is a critical challenge in re…

cs.CL2025

Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study

Xuefeng Jiang, Lvhua Wu, Sheng Sun +5

Code vulnerability detection (CVD) is essential for addressing and preventing system security issues, playing a crucial role in ensuring software security. Previous learning-based…

cs.LG2023

Online Spatio-Temporal Correlation-Based Federated Learning for Traffic Flow Forecasting

Qingxiang Liu, Sheng Sun, Min Liu +2

Traffic flow forecasting (TFF) is of great importance to the construction of Intelligent Transportation Systems (ITS). To mitigate communication burden and tackle with the problem…

cs.DC2025

EC2MoE: Adaptive End-Cloud Pipeline Collaboration Enabling Scalable Mixture-of-Experts Inference

Zheming Yang, Yunqing Hu, Sheng Sun +1

The Mixture-of-Experts (MoE) paradigm has emerged as a promising solution to scale up model capacity while maintaining inference efficiency. However, deploying MoE models across he…