Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Wei ChenSuggested from co-authorship
- Lifang HeSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works196 from public data
- SplitFed: When Federated Learning Meets Split Learning1,007
A novel approach is presented, named splitfed learning (SFL), that amalgamates the two approaches eliminating their inherent drawbacks, along with a refined architectural configuration incorporating differential privacy and PixelDP to enhance data privacy and model robustness.
- A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT868
This survey provides a comprehensive review on the history of generative models, and basic components, recent advances in AIGC from unimmodal interaction and multimodal interaction, and introduces the generation tasks and relative models of text and image.
- Membership Inference Attacks on Machine Learning: A Survey746
This article provides the taxonomies for both attacks and defenses, based on their characterizations, and discusses their pros and cons, and point out several promising future research directions to inspire the researchers who wish to follow this area.
- Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models734
This paper presents a comprehensive review of the model's background, related technologies, applications, remaining challenges, and future directions of text-to-video AI models.
- 607
- Privacy and Robustness in Federated Learning: Attacks and Defenses582
A comprehensive survey on privacy and robustness in FL over the past five years is conducted and a concise introduction to the concept of FL is provided and a unique taxonomy covering privacy attacks and defenses is provided.
- A Survey on Text Classification: From Traditional to Deep Learning580
A taxonomy for text classification according to the text involved and the models used for feature extraction and classification is created, dealing with both the technical developments and benchmark datasets that support tests of predictions.
- A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPT554
This survey aims to shed light on the research of the PFMs on scalability, security, logical reasoning ability, cross-domain learning ability, cross-domain learning ability, and user-friendly interactive ability for artificial general intelligence.
- A generalist vision–language foundation model for diverse biomedical tasks469
BiomedGPT is described, the first open-source and lightweight vision–language foundation model, designed as a generalist capable of performing various biomedical tasks, which achieves state-of-the-art accuracy in 16 out of 25 biomedical tasks, with promising performance in a series of potential clinical applications.
- Adversarial Attack and Defense on Graph Data: A Survey409
This review is intended to provide an overall landscape of more than 100 papers on adversarial attack and defense strategies for graph data, and establish a unified formulation encompassing most graph adversarial learning models.
- Decentralized Federated Learning: A Survey and Perspective362
A systematic and detailed perspective on DFL, including iteration order, communication protocols, network topologies, paradigm proposals, and temporal variability, and several extended variants and categorizations are proposed with state-of-the-art (SOTA) technologies.
- User Preference-aware Fake News Detection357
A new framework, UPFD, is proposed, which simultaneously captures various signals from user preferences by joint content and graph modeling, and demonstrates the effectiveness of the proposed framework on real-world datasets.
- AugGPT: Leveraging ChatGPT for Text Data Augmentation316
Experimental results on multiple few-shot learning text classification tasks show the superior performance of the proposed AugGPT approach over state-of-the-art text data augmentation methods in terms of testing accuracy and distribution of the augmented samples.
- LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy282
A novel design of local differential privacy mechanism for federated learning that makes the local weights update differentially private by adapting to the varying ranges at different layers of a deep neural network, which introduces a smaller variance of the estimated model weights, especially for deeper models.
- MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use244
MetaTool is introduced, a benchmark designed to evaluate whether LLMs have tool usage awareness and can correctly choose tools, and recommends that tool developers choose an appropriate rewrite model for generating new descriptions based on the downstream LLM the tool will apply to.
- Optimization-based Prompt Injection Attack to LLM-as-a-Judge237
This work proposes JudgeDeceiver, an optimization-based prompt injection attack to LLM-as-a-Judge that injects a carefully crafted sequence into an attacker-controlled candidate response such that LLM-as-a-Judge selects the candidate response for an attacker-chosen question no matter what other candidate responses are.
- MA-SAM: Modality-agnostic SAM adaptation for 3D medical image segmentation235
A modality-agnostic SAM adaptation framework that is applicable to various volumetric and video medical data is introduced, and without using any prompt, consistently outperforms various state-of-the-art 3D approaches.
- A Survey of AI-Generated Content (AIGC)220
This survey provides a comprehensive review of the history of generative models and recent advances in AIGC, focusing on both unimodal and multimodal interaction.
- FedBERT : When Federated Learning Meets Pre-training182
This work proposes a new learning approach, FedBERT, that takes advantage of the federated learning and split learning approaches, resorting to pre-training BERT in a federated way and can prevent sharing the raw data information and obtain excellent performance.
- End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models172
The first to build the benchmark dataset and solutions for end-to-end multimodal fact-checking and explanation generation and to establish baseline performances on MOCHEG, it is demonstrated that the performance of the state-of-the-art end- to-end multi-million-dollar fact- checking does not provide satisfactory outcomes.
- Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks156
The studies show that mixup is a domain-independent data augmentation technique to pre-trained language models, resulting in significant performance improvement for transformer-based models.
- 137
- Federated Model Distillation with Noise-Free Differential Privacy135
This paper proposes a novel framework called FEDMD-NFDP, which applies a Noise-FreeDifferential Privacy (NFDP) mechanism into a federated model distillation framework, and demonstrates the feasibility of this framework by considering both IID and Non-IID settings, heterogeneous model architectures, and unlabelled public datasets from a different distribution.
- Private Model Compression via Knowledge Distillation133
A private model compression framework RONA, which jointly uses hint learning, distillation learning, and self learning to train a compact and fast neural network, which can not only compress cumbersome models efficiently but also provide a strong privacy guarantee.
- 127
- Personalized Edge Intelligence via Federated Self-Knowledge Distillation127
A novel Personalized Federated Learning framework via self-knowledge distillation, named pFedSD, which accelerates the process of recalling the personalized knowledge for the latest initialized clients by allowing clients to distill the knowledge of previous personalized models to current local models.
- Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!125
This work presents how an adversary can steal a BERT-based API service (the victim/target model) on multiple benchmark datasets with limited prior knowledge and queries, and shows that the extracted model can lead to highly transferable adversarial attacks against the victim model.
- Source Inference Attacks in Federated Learning124
A new inference attack called source inference attack (SIA) is proposed, which can derive an optimal estimation of the source of a training member and leverages the prediction loss of local models on the training members to achieve the attack effectively and non-intrusively.
- MetaAgents: Large Language Model Based Agents for Decision-Making on Teaming121
MetaAgents, a social simulation framework populated with LLM-based agents, is introduced, demonstrating that LLM-based agents perform competently in making rational decisions to develop efficient teams and identifying limitations that hinder their effectiveness in more complex team assembly tasks.
- BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT115
This study proposes BadGPT, the first backdoor attack against RL fine-tuning in language models, by injecting a backdoor into the reward model, so that the language model can be compromised during the fine- Tuning stage.
- Deep Learning towards Mobile Applications112
An overview of the current challenges and representative achievements about pushing deep learning on mobile devices from three aspects: training with mobile data, efficient inference onMobile devices, and applications of mobile deep learning.
- Privacy-Preserving Federated Depression Detection From Multisource Mobile Health Data109
A general multiview federated learning framework using multisource data is proposed, which can extend any traditional machine learning model to support Federated learning across different institutions or parties and later fusion methods are employed to solve the problem of inconsistent time series of multIView data.
- 105
- Multi-Round Influence Maximization100
This paper designs scalable algorithms based on the reverse influence sampling approach and achieves near-linear running time for the Multi-Round Influence Maximization (MRIM) problem, where influence propagates in multiple rounds independently from possibly different seed sets.
- 96
- You see what I want you to see: poisoning vulnerabilities in neural code search94
This work studies and develops a series of backdoor attacks on the deep-learning-based models for code search, through data poisoning, and introduces a simple yet effective attack on neural code search models by poisoning their corresponding training dataset.
- Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts83
This work discovers a system prompt leakage vulnerability in GPT-4V and proposes a novel MLLM jailbreaking attack method termed SASP (Self-Adversarial Attack via System Prompt), demonstrating the important role of system prompts in jailbreaking.
- Hawk: Rapid Android Malware Detection Through Heterogeneous Graph Attention Networks82
Hawk is presented, a new malware detection framework for evolutionary Android applications that model Android entities and behavioral relationships as a heterogeneous information network (HIN), exploiting its rich semantic meta-structures for specifying implicit higher order relationships.
- Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V75
The experiments with accuracy score conclude that the current version of GPT-4V is not recommended for real-world diagnostics due to its unreliable and suboptimal accuracy in responding to diagnostic medical questions.
- Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding74
This work proposes a novel event extraction framework that uses event types and argument roles as natural language queries to extract candidate triggers and arguments from the input text and significantly outperforms existing methods on zero-shot event extraction.
- 74
- 71
- 70
- 69
- Transferable Unlearnable Examples64
A novel unlearnable strategy based on Classwise Separability Discriminant (CSD) is proposed, which aims to better transfer the Unlearnable effects to other training settings and datasets by enhancing the linear separability.
- Attacking Fake News Detectors via Manipulating News Social Engagement63
This paper presents the first adversarial attack framework against Graph Neural Network (GNN)-based fake news detectors to probe their robustness and leverages a multi-agent reinforcement learning (MARL) framework to simulate the adversarial behavior of fraudsters on social media.
- DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN62
This paper proposes Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN (DSKReG) that learns the relevance distribution of connected items from KGs and samples suitable items for recommendation following this distribution.
- On the Trustworthiness of Generative Foundation Models: Guideline, Assessment, and Perspective60
A holistic framework for advancing trustworthiness in GenAI is established, paving the way for safer and more responsible integration of GenFMs into critical applications and releasing the toolkit for dynamic evaluation.
- Joint Embedding of Structural and Functional Brain Networks with Graph Neural Networks for Mental Illness Diagnosis57
This work develops a novel multiview GNN model which takes advantage of the message passing scheme by propagating messages based on degree statistics and brain region connectivities and employs contrastive learning for multimodal fusion.
- Secure Deep Graph Generation with Link Differential Privacy54
This paper leverage the differential privacy (DP) framework to formulate and enforce rigorous privacy constraints on deep graph generation models, with a focus on edge-DP to guarantee individual link privacy.
- Individualized Short-Term Electric Load Forecasting Using Data-Driven Meta-Heuristic Method Based on LSTM Network53
Simulation results demonstrate that the multiple forecasts with MetaREC_long short-term memory can effectively incentivize the high accuracy and stability for short- term power load forecasting.
- Federated Multi-view Learning for Private Medical Data Integration and Analysis52
A generic Federated Multi-view Learning (FedMV) framework that is the first to consider both vertical and horizontal diversification in the multi-view setting, as well as their sequential federated learning.
- Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models51
This paper makes the first attempt to build a universal attacker against real-world LVLMs, focusing on two critical aspects: restricting access to only the LVLM inputs and outputs and devising a universal adversarial patch, which is task-agnostic and can deceive any LVLM-driven task when applied to various inputs.
- Sequential Keystroke Behavioral Biometrics for Mobile User Identification via Multi-view Deep Learning49
This paper proposes DEEPSERVICE, a new technique that can identify mobile users based on user's keystroke information captured by a special keyboard or web browser and is highly accurate in identifying mobile users (over 93% accuracy).
- Source Inference Attacks: Beyond Membership Inference Attacks in Federated Learning44
A new inference attack is proposed, designed to facilitate an honest-but-curious server to identify the training record's source client and leverage the Bayesian theorem to implement the attack in a non-intrusive manner without deviating from the defined FL protocol.
- Graph Entropy Guided Node Embedding Dimension Selection for Graph Neural Networks43
This paper revisits NEDS from the perspective of minimum entropy principle and proposes a novel Minimum Graph Entropy (MinGE) algorithm, which considers both feature entropy and structure entropy on graphs, which are carefully designed according to the characteristics of the rich information in them.
- DroidClassifier: Efficient Adaptive Mining of Application-Layer Header for Classifying Android Malware39
DroidClassifier can facilitate network management in a large network, and enable unobtrusive detection of mobile malware, and is expected to work with reasonable accuracy for other mobile platforms such as iOS and Windows Mobile as well.
- 37
- Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks36
This work proposesMEta-GrAph-based network embedding models, called MEGA and MEGA++, respectively, which uses normalized relevance or similarity measures that are derived from a meta-graph and its embedded meta-paths between nodes simultaneously, and then leverages tensor decomposition method to perform node embedding.
- RAIN: RegulArization on Input and Network for Black-Box Domain Adaptation35
This paper proposes a novel approach named RAIN (RegulArization on Input and Network) for Black-Box domain adaptation from both input-level and network-level regularization, which alleviates overfitting on the source domain by learning diverse target representations.
- 34
- 30
- 29
- 28
- 23
- 21
- BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models20
This work proposes BadToken, the first token-level backdoor attack to MLLMs, and introduces two novel backdoor behaviors: Token-substitution and Token-addition, which enable flexible and stealthy attacks by making token-level modifications to the original output for backdoored inputs.
- 20
- 19
- 18
- Backdoor Attacks on Crowd Counting17
This paper proposes two novel Density Manipulation Backdoor Attacks (DMBA- and DMBA+) to attack the model to produce arbitrarily large or small density estimations, and provides an in-depth analysis of the unique challenges of backdooring crowd counting models.
- 17
- 16
- 15
- 13
- Backdoor Attacks to Pre-trained Unified Foundation Models13
This paper makes proof-of-concept level research on the backdoor attack for pre-trained unified foundation models and reveals the vulnerability of these models and suggests future research directions for enhancing the attack approach.
- 13
- 13
- 12
- 12
- 12
- 12
- 11
- 11
- 10
- 10
- 10
- 9
- 9
- Improving Interpretation Faithfulness for Vision Transformers9
This paper proposes a new method called Denoised Diffusion Smoothing (DDS), which adopts randomized smoothing and diffusion-based denoising and shows that processing ViTs directly with DDS can turn them into Faithful ViTs.
- 9
- 8
- 8
- 8
- Robust Computer Vision in an Ever-Changing World: A Survey of Techniques for Tackling Distribution Shifts8
An in-depth overview of various types of distribution shifts is provided, elucidate their distinctions, and techniques within the realm of the data-centric domain employed to address them are explored.
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- Unlearnable Graph: Protecting Graphs from Unauthorized Exploitation6
A novel method for generating unlearnable graph examples by injecting delusive but imperceptible noise into graphs using the authors' Error-Minimizing Structural Poisoning (EMinS) module, which is able to make the graphs unexploitable.
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- GraphCloak: Safeguarding Task-specific Knowledge within Graph-structured Data from Unauthorized Exploitation5
GraphCloak is introduced to safeguard against the unauthorized usage of graph data by proposing two error-minimizing-based poisoning methods that target perturbations on the structural and feature space, along with a subgraph injection poisoning method.
- 5
- 5
- 5
- 5
- 4
- 4
- The Role of Computing Resources in Publishing Foundation Model Research4
It is found that increased computing is correlated with national funding allocations and citations, but the findings don't observe the strong correlations with research environment (academic or industrial), domain, or study methodology.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- The 1st International Workshop on Federated Learning with Graph Data (FedGraph)–
The nascent field of federated learning (FL), which aims to enable individual clients to jointly train their models while keeping their local data decentralized and completely private, is a promising paradigm for large-scale distributed and private training of GNNs.
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.