YLYi Liu

Yi Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yi Liu has a total of 69 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    FedKDD/FedMAS 2026: The 2026 International Joint Workshop on Federated Learning for Multi-agent Systems and Data Mining

    by Haozhao Wang, Zhuangdi Zhu, Zheng Xu, Yi Liu, Dongyuan Li, Ming Hu, Mingyue Cheng, Junyuan Hong, Nathalie Baracaldo, Neil Shah, et al.

    Multi-agent systems (MAS) are enabling increasingly complex, collaborative applications in autonomous driving, smart logistics, robotic coordination, and distributed sensing. Their effectiveness depends on collective intelligence emerging from multiple distributed agents, each operating with partial information and often sensitive local data. To realize such collaboration while preserving data privacy and autonomy, federated learning (FL) has emerged as a de facto decentralized framework that allows agents to learn shared models without centralizing raw data. Despite the rapid progress in both FL and MAS, significant challenges remain in integrating these paradigms—such as coordinating heterogeneous agents, handling non-IID data, ensuring communication efficiency, and maintaining system robustness and fairness in open environments. This workshop seeks to bring together researchers and practitioners from academia and industry to explore the convergence of federated learning and multi-agent systems. We aim to foster discussions on foundational advances, real-world deployments, and emerging interdisciplinary opportunities, with a focus on scalability, trustworthiness, adaptive coordination, and the broader societal impact of federated multi-agent intelligence.

  • Open Access

    Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation

    by Yingjia Shang, Yi Liu, Huimin Wang, Furong Li, Wenfang Sun, Chengyu Wu, Yefeng Zheng

    With the rapid advancement of retrieval-augmented vision-language models, multimodal medical retrieval-augmented generation (MMed-RAG) systems are increasingly adopted in clinical decision support. These systems enhance medical applications by performing cross-modal retrieval to integrate relevant visual and textual evidence for tasks, e.g., report generation and disease diagnosis. However, their complex architecture also introduces underexplored adversarial vulnerabilities, particularly via visual input perturbations. In this paper, we propose Medusa, a novel framework for crafting cross-modal transferable adversarial attacks on MMed-RAG systems under a black-box setting. Specifically, Medusa formulates the attack as a perturbation optimization problem, leveraging a multi-positive InfoNCE loss (MPIL) to align adversarial visual embeddings with medically plausible but malicious textual targets, thereby hijacking the retrieval process. To enhance transferability, we adopt a surrogate model ensemble and design a dual-loop optimization strategy augmented with invariant risk minimization (IRM). Extensive experiments on two real-world medical tasks, including medical report generation and disease diagnosis, demonstrate that Medusa achieves over 90% average attack success rate across various generation models and retrievers under appropriate parameter configuration, while remaining robust against four mainstream defenses, outperforming state-of-the-art baselines. Our results reveal critical vulnerabilities in the MMed-RAG systems and highlight the necessity of robustness benchmarking in safety-critical medical applications. The code and data are available at https://github.com/yiliucs/MMed-RAG-Attack.


  • Open Access

    Reconstructing Training Data from Adapter-based Federated Large Language Models

    by Silong Chen, Yuchuan Luo, Guilin Deng, Yi Liu, Ming Xu, Shaojing Fu, Xiaohua Jia

    Adapter-based Federated Large Language Models (FedLLMs) are widely adopted to reduce the computational, storage, and communication overhead of full-parameter fine-tuning for web-scale applications while preserving user privacy. By freezing the backbone and training only compact low-rank adapters, these methods appear to limit gradient leakage and thwart existing Gradient Inversion Attacks (GIAs). Contrary to this assumption, we show that low-rank adapters create new, exploitable leakage channels. We propose the Unordered-word-bag-based Text Reconstruction (UTR) attack, a novel GIA tailored to the unique structure of adapter-based FedLLMs. UTR overcomes three core challenges—low-dimensional gradients, frozen backbones, and combinatorially large reconstruction spaces—by: (i) inferring token presence from attention patterns in frozen layers, (ii) performing sentence-level inversion within the low-rank subspace of adapter gradients, and (iii) enforcing semantic coherence through constrained greedy decoding guided by language priors. Extensive experiments across diverse models (GPT2-Large, BERT, Qwen2.5-7B) and datasets (CoLA, SST-2, Rotten Tomatoes) demonstrate that UTR achieves near-perfect reconstruction accuracy (ROUGE-1/2 > 99), even with large batch sizes—settings where prior GIAs fail completely. Our results reveal a fundamental tension between parameter efficiency and privacy in FedLLMs, challenging the prevailing belief that lightweight adaptation inherently enhances security. Our code and data are available at https://github.com/shwksnshwowk-wq/GIA


  • Open Access

    Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts

    by Yi Liu, Chengjun Cai, Xiaoli Zhang, Xingliang Yuan, Cong Wang

    Large Vision Language Models (VLMs) extend and enhance the perceptual abilities of Large Language Models (LLMs). Despite offering new possibilities for LLM applications, these advancements raise significant security and ethical concerns, particularly regarding the generation of harmful content. While LLMs have undergone extensive security evaluations with the aid of red teaming frameworks, VLMs currently lack a well-developed one. To fill this gap, we introduce Arondight, a standardized red team framework tailored specifically for VLMs. Arondight is dedicated to resolving issues related to the absence of visual modality and inadequate diversity encountered when transitioning existing red teaming methodologies from LLMs to VLMs. Our framework features an automated multi-modal jailbreak attack, wherein visual jailbreak prompts are produced by a red team VLM, and textual prompts are generated by a red team LLM guided by a reinforcement learning agent. To enhance the comprehensiveness of VLM security evaluation, we integrate entropy bonuses and novelty reward metrics. These elements incentivize the RL agent to guide the red team LLM in creating a wider array of diverse and previously unseen test cases. Our evaluation of ten cutting-edge VLMs exposes significant security vulnerabilities, particularly in generating toxic images and aligning multi-modal prompts. In particular, our Arondight achieves an average attack success rate of 84.5% on GPT-4 in all fourteen prohibited scenarios defined by OpenAI in terms of generating toxic text. For a clearer comparison, we also categorize existing VLMs based on their safety levels and provide corresponding reinforcement recommendations. Our multimodal prompt dataset and red team code will be released after ethics committee approval. CONTENT WARNING: THIS PAPER CONTAINS HARMFUL MODEL RESPONSES.


  • Open Access

    BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning

    by Yi Liu, Cong Wang, Xingliang Yuan

    Federated Learning (FL) is susceptible to poisoning attacks, wherein compromised clients manipulate the global model by modifying local datasets or sending manipulated model updates. Experienced defenders can readily detect and mitigate the poisoning effects of malicious behaviors using Byzantine-robust aggregation rules. However, the exploration of poisoning attacks in scenarios where such behaviors are absent remains largely unexplored for Byzantine-robust FL. This paper addresses the challenging problem of poisoning Byzantine-robust FL by introducing catastrophic forgetting. To fill this gap, we first formally define generalization error and establish its connection to catastrophic forgetting, paving the way for the development of a clean-label data poisoning attack named BadSampler. This attack leverages only clean-label data (i.e., without poisoned data) to poison Byzantine-robust FL and requires the adversary to selectively sample training data with high loss to feed model training and maximize the model's generalization error. We formulate the attack as an optimization problem and present two elegant adversarial sampling strategies, Top-k sampling, and meta-sampling, to approximately solve it. Additionally, our formal error upper bound and time complexity analysis demonstrate that our design can preserve attack utility with high efficiency. Extensive evaluations on two real-world datasets illustrate the effectiveness and performance of our proposed attacks.


  • Open Access

    MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction

    by Wangjie Jiang, Zhihao Ye, Zijing Ou, Ruihui Zhao, Jianguang Zheng, Yi Liu, Siheng Li, Bang Liu, Yujiu Yang, Yefeng Zheng

    Chinese Spelling Correction (CSC) is gaining increasing attention due to its promise of automatically detecting and correcting spelling errors in Chinese texts. Despite its extensive use in many applications, like search engines and optical character recognition systems, little has been explored in medical scenarios in which complex and uncommon medical entities are easily misspelled. Correcting the misspellings of medical entities is arguably more difficult than those in the open domain due to its requirements of specificdomain knowledge. In this work, we define the task of Medical-domain Chinese Spelling Correction and propose MCSCSet, a large scale specialist-annotated dataset that contains about 200k samples. In contrast to the existing open-domain CSC datasets, MCSCSet involves: i) extensive real-world medical queries collected from Tencent Yidian, ii) corresponding misspelled sentences manually annotated by medical specialists. To ensure automated dataset curation, MCSCSet further offers a medical confusion set consisting of the commonly misspelled characters of given Chinese medical terms. This enables one to create the medical misspelling dataset automatically. Extensive empirical studies have shown significant performance gaps between the open-domain and medical-domain spelling correction, highlighting the need to develop high-quality datasets that allow for Chinese spelling correction in specific domains. Moreover, our work benchmarks several representative Chinese spelling correction models, establishing baselines for future work.

  • Cross-Area Travel Time Uncertainty Estimation From Trajectory Data: A Federated Learning Approach

    by Yuanshao Zhu, Yongchao Ye, Yi Liu, James J. Q. Yu

    Along with urbanization and the deployment of GPS sensors in vehicles and mobile phones, massive amounts of trajectory data have been generated for city areas. The analysis of these data has substantially contributed to research and advancements of travel time estimation. However, existing work focuses on estimating travel time inside a particular area, and cross-area travel time estimation has privacy security challenges due to data exchange issues among areas. Meanwhile, the majority of methods estimate a deterministic travel time for a given trajectory, which does not account for complex traffic situations and user requirements. To address these problems, we propose a cross-area travel time uncertainty estimation algorithm for estimating the uncertainty of travel times while preserving privacy among different areas. Specifically, we design a comprehensive cross-area privacy-preserving solution that trains a tailor-made neural network travel time estimator in each area by local data, and incorporates federated learning for training. Furthermore, we employ Bayesian deep learning principles and adopt Monte-Carlo dropout to quantify the uncertainty associated with travel time. To evaluate the proposed approach, we conduct a series of comprehensive case studies with two real-world trajectory datasets. Extensive results demonstrate the superiority of the proposed approach compared to baselines in the context of the cross-area setting.


  • Communication-Efficient and Cross-Chain Empowered Federated Learning for Artificial Intelligence of Things

    by Jiawen Kang, Xuandi Li, Jiangtian Nie, Yi Liu, Minrui Xu, Zehui Xiong, Dusit Niyato, Qiang Yan

    Conventional machine learning approaches aggregate all training data in a central server, which causes massive communication overhead of data transmission and is also vulnerable to privacy leakage. Thereby, blockchain-based federated learning has emerged to protect Artificial Intelligence of Things (AIoT) devices from exposing their private data by the Federated Learning (FL) framework, and also enables decentralized model training without the vulnerability of a central server. However, the existing blockchain-based FL systems still suffer from (i) limited scalability of the single blockchain framework; and (ii) large communication costs incurred by iterative large-size model update transmission. To this end, we first design an efficient cross-chain framework for scalable and flexible model training management, in which multiple blockchains are customized for specific FL tasks and individually perform learning tasks for privacy protection. A cross-chain scheme is proposed to enable secure blockchain collaboration and interactions for efficient model training, model trading, and payment. We then propose a flexible model update compression scheme to save communication costs almost without compromising accuracy. Moreover, for model trading markets, we design a dynamic pricing scheme using machine learning-based auction for model trading. Numerical results demonstrate that the proposed framework and schemes achieve scalable, flexible, and communication-efficient decentralized FL systems in AIoT.


  • Top Cited Papers

    Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization

    by Yifeng Zheng, Shangqi Lai, Yi Liu, Xingliang Yuan, Xun Yi, Cong Wang

    Federated learning has recently emerged as a paradigm promising the benefits of harnessing rich data from diverse sources to train high quality models, with the salient features that training datasets never leave local devices. Only model updates are locally computed and shared for aggregation to produce a global model. While federated learning greatly alleviates the privacy concerns as opposed to learning with centralized data, sharing model updates still poses privacy risks. In this paper, we present a system design which offers efficient protection of individual model updates throughout the learning procedure, allowing clients to only provide obscured model updates while a cloud server can still perform the aggregation. Our federated learning system first departs from prior works by supporting lightweight encryption and aggregation, and resilience against drop-out clients with no impact on their participation in future rounds. Meanwhile, prior work largely overlooks bandwidth efficiency optimization in the ciphertext domain and the support of security against an actively adversarial cloud server, which we also fully explore in this paper and provide effective and efficient mechanisms. Extensive experiments over several benchmark datasets (MNIST, CIFAR-10, and CelebA) show our system achieves accuracy comparable to the plaintext baseline, with practical performance.