Search Results for author: Cen Chen

Found 76 papers, 32 papers with code

Boosting Gradient Leakage Attacks: Data Reconstruction in Realistic FL Settings

no code implementations10 Jun 2025 Mingyuan Fan, Fuyi Wang, Cen Chen, Jianying Zhou

Federated learning (FL) enables collaborative model training among multiple clients without the need to expose raw data.

Federated Learning

Responsible Diffusion Models via Constraining Text Embeddings within Safe Regions

1 code implementation21 May 2025 Zhiwen Li, Die Chen, Mingyuan Fan, Cen Chen, Yaliang Li, Yanhao Wang, Wenmeng Zhou

In this paper, we propose a novel self-discovery approach to identifying a semantic direction vector in the embedding space to restrict text embedding within a safe region.

Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models

no code implementations21 May 2025 Die Chen, Zhiwen Li, Cen Chen, Yuexiang Xie, Xiaodan Li, Jinyan Ye, Yingda Chen, Yaliang Li

Text-to-image diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential.

Reinforced MLLM: A Survey on RL-Based Reasoning in Multimodal Large Language Models

no code implementations30 Apr 2025 Guanghao Zhou, Panjia Qiu, Cen Chen, Jie Wang, Zheming Yang, Jian Xu, Minghui Qiu

The application of reinforcement learning (RL) to enhance the reasoning capabilities of Multimodal Large Language Models (MLLMs) constitutes a rapidly advancing research area.

Multimodal Reasoning Reinforcement Learning (RL)

Semantic Shift Estimation via Dual-Projection and Classifier Reconstruction for Exemplar-Free Class-Incremental Learning

1 code implementation7 Mar 2025 Run He, Di Fang, Yicheng Xu, Yawen Cui, Ming Li, Cen Chen, Ziqian Zeng, Huiping Zhuang

Specifically, the embeddings of old tasks shift in the embedding space after learning new tasks, and the classifier becomes biased towards new tasks due to training solely with new data, hindering the balance between old and new knowledge.

class-incremental learning Class Incremental Learning +3

RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis

no code implementations23 Feb 2025 Jianwei Wang, Junyao Yang, Haoran Li, Huiping Zhuang, Cen Chen, Ziqian Zeng

The success of large language models (LLMs) has attracted many individuals to fine-tune them for domain-specific tasks by uploading their data.

Code Generation Privacy Preserving +1

SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings

1 code implementation18 Feb 2025 Weikai Lu, Hao Peng, Huiping Zhuang, Cen Chen, Ziqian Zeng

Multimodal Large Language Models (MLLMs) have serious security vulnerabilities. While safety alignment using multimodal datasets consisting of text and data of additional modalities can effectively enhance MLLM's security, it is costly to construct these datasets.

Safety Alignment

Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion Models

no code implementations18 Feb 2025 Die Chen, Zhiwen Li, Cen Chen, Xiaodan Li, Jinyan Ye

At the tool level, we perform a detailed toxicity analysis of NSFW datasets and compare the performance of different NSFW classifiers, offering deeper insights into their performance alongside a compilation of comprehensive evaluation metrics.

CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models

no code implementations17 Feb 2025 Guanghao Zhou, Panjia Qiu, Mingyuan Fan, Cen Chen, Mingyuan Chu, Xin Zhang, Jun Zhou

We define jailbreak attacks as an optimization problem within the embedding space of masked language models.

Combinatorial Optimization

Bad-PFL: Exploring Backdoor Attacks against Personalized Federated Learning

no code implementations22 Jan 2025 Mingyuan Fan, Zhanyi Hu, Fuyi Wang, Cen Chen

Data heterogeneity and backdoor attacks rank among the most significant challenges facing federated learning (FL).

Personalized Federated Learning

SVIA: A Street View Image Anonymization Framework for Self-Driving Applications

1 code implementation16 Jan 2025 Dongyu Liu, Xuhong Wang, Cen Chen, Yanhao Wang, Shengyue Yao, Yilun Lin

In recent years, there has been an increasing interest in image anonymization, particularly focusing on the de-identification of faces and individuals.

De-identification Image Generation

Privacy Evaluation Benchmarks for NLP Models

1 code implementation24 Sep 2024 Wei Huang, Yinggui Wang, Cen Chen

In this paper, we present a privacy attack and defense evaluation benchmark in the field of NLP, which includes the conventional/small models and large language models (LLMs).

Knowledge Distillation

FedMCP: Parameter-Efficient Federated Learning with Model-Contrastive Personalization

no code implementations28 Aug 2024 Qianyi Zhao, Chen Qu, Cen Chen, Mingyuan Fan, Yanhao Wang

Specifically, FedMCP adds two lightweight adapter modules, i. e., the global adapter and the private adapter, to the frozen PLMs within clients.

Federated Learning parameter-efficient fine-tuning

AIR: Analytic Imbalance Rectifier for Continual Learning

2 code implementations19 Aug 2024 Di Fang, Yinan Zhu, Runze Fang, Cen Chen, Ziqian Zeng, Huiping Zhuang

To solve this problem, we propose an analytic imbalance rectifier algorithm (AIR), a novel online exemplar-free continual learning method with an analytic (i. e., closed-form) solution for data-imbalanced class-incremental learning (CIL) and generalized CIL scenarios in real-world continual learning.

class-incremental learning Class Incremental Learning +2

EIUP: A Training-Free Approach to Erase Non-Compliant Concepts Conditioned on Implicit Unsafe Prompts

no code implementations2 Aug 2024 Die Chen, Zhiwen Li, Mingyuan Fan, Cen Chen, Wenmeng Zhou, Yaliang Li

Since image generation is conditioned on text, prompt purification serves as a straightforward solution for content safety.

Image Generation

SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images

no code implementations13 Jul 2024 Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu

On average, SemiAdv only needs to query a few hundred times to launch an effective attack with more than 90% success rate.

Adversarial Attack

GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language Models

1 code implementation20 Jun 2024 Tao Zhang, Ziqian Zeng, Yuxiang Xiao, Huiping Zhuang, Cen Chen, James Foulds, SHimei Pan

Furthermore, we categorized the gender biases in the "rejected" responses of GenderAlign into 4 principal categories.

8k

ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning

1 code implementation20 Jun 2024 Zhongjie Duan, Wenmeng Zhou, Cen Chen, Yaliang Li, Weining Qian

To evaluate the efficacy of our proposed post-tuning approach, we conduct extension training on the Stable Video Diffusion model.

Video Generation

DPSW-Sketch: A Differentially Private Sketch Framework for Frequency Estimation over Sliding Windows (Technical Report)

no code implementations12 Jun 2024 Yiping Wang, Yanhao Wang, Cen Chen

The sliding window model of computation captures scenarios in which data are continually arriving in the form of a stream, and only the most recent $w$ items are used for analysis.

PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration

no code implementations3 Jun 2024 Ziqian Zeng, Jianwei Wang, Junyao Yang, Zhengdong Lu, Haoran Li, Huiping Zhuang, Cen Chen

The widespread usage of online Large Language Models (LLMs) inference services has raised significant privacy concerns about the potential exposure of private information in user inputs to malicious eavesdroppers.

Privacy Preserving

GACL: Exemplar-Free Generalized Analytic Continual Learning

2 code implementations23 Mar 2024 Huiping Zhuang, Yizhu Chen, Di Fang, Run He, Kai Tong, Hongxin Wei, Ziqian Zeng, Cen Chen

The GACL adopts analytic learning (a gradient-free training technique) and delivers an analytical (i. e., closed-form) solution to the GCIL scenario.

class-incremental learning Class Incremental Learning +2

REAL: Representation Enhanced Analytic Learning for Exemplar-free Class-incremental Learning

no code implementations20 Mar 2024 Run He, Huiping Zhuang, Di Fang, Yizhu Chen, Kai Tong, Cen Chen

The DS-BPT pretrains model in streams of both supervised learning and self-supervised contrastive learning (SSCL) for base knowledge extraction.

class-incremental learning Class Incremental Learning +3

Learning Knowledge-Enhanced Contextual Language Representations for Domain Natural Language Understanding

no code implementations12 Nov 2023 Ruyao Xu, Taolin Zhang, Chengyu Wang, Zhongjie Duan, Cen Chen, Minghui Qiu, Dawei Cheng, Xiaofeng He, Weining Qian

In the experiments, we evaluate KANGAROO over various knowledge-aware and general NLP tasks in both full and few-shot learning settings, outperforming various KEPLM training paradigms performance in closed-domains significantly.

Contrastive Learning Data Augmentation +4

Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness

1 code implementation10 Nov 2023 Mingyuan Fan, Xiaodan Li, Cen Chen, Wenmeng Zhou, Yaliang Li

A prevailing belief in attack and defense community is that the higher flatness of adversarial examples enables their better cross-model transferability, leading to a growing interest in employing sharpness-aware minimization and its variants.

Adversarial Attack Diversity

PAI-Diffusion: Constructing and Serving a Family of Open Chinese Diffusion Models for Text-to-image Synthesis on the Cloud

no code implementations11 Sep 2023 Chengyu Wang, Zhongjie Duan, Bingyan Liu, Xinyi Zou, Cen Chen, Kui Jia, Jun Huang

Text-to-image synthesis for the Chinese language poses unique challenges due to its large vocabulary size, and intricate character relationships.

Image Generation Style Transfer

TransPrompt v2: A Transferable Prompting Framework for Cross-task Text Classification

no code implementations29 Aug 2023 Jianing Wang, Chengyu Wang, Cen Chen, Ming Gao, Jun Huang, Aoying Zhou

We propose TransPrompt v2, a novel transferable prompting framework for few-shot learning across similar or distant text classification tasks.

Few-Shot Learning Few-Shot Text Classification +1

On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook

no code implementations31 Jul 2023 Mingyuan Fan, Chengyu Wang, Cen Chen, Yang Liu, Jun Huang

Diffusion models and large language models have emerged as leading-edge generative models, revolutionizing various aspects of human life.

Fairness

UPFL: Unsupervised Personalized Federated Learning towards New Clients

no code implementations29 Jul 2023 Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao

To address this challenge, we extend the adaptive risk minimization technique into the unsupervised personalized federated learning setting and propose our method, FedTTA.

Knowledge Distillation Personalized Federated Learning

You Can Backdoor Personalized Federated Learning

1 code implementation29 Jul 2023 Tiandi Ye, Cen Chen, Yinggui Wang, Xiang Li, Ming Gao

The resistance of pFL methods with parameter decoupling is attributed to the heterogeneous classifiers between malicious clients and benign counterparts.

Backdoor Attack Meta-Learning +1

CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation

1 code implementation ICCV 2023 Lizhao Liu, Zhuangwei Zhuang, Shangxin Huang, Xunlong Xiao, Tianhang Xiang, Cen Chen, Jingdong Wang, Mingkui Tan

CMT disentangles the learning of supervised segmentation and unsupervised masked context prediction for effectively learning the very limited labeled points and mass unlabeled points, respectively.

Representation Learning Scene Understanding +2

On the Robustness of Split Learning against Adversarial Attacks

no code implementations16 Jul 2023 Mingyuan Fan, Cen Chen, Chengyu Wang, Wenmeng Zhou, Jun Huang

Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i. e., sever and clients only hold partial sub-networks and exchange intermediate computations).

Adversarial Attack

Optimal Linear Subspace Search: Learning to Construct Fast and High-Quality Schedulers for Diffusion Models

1 code implementation24 May 2023 Zhongjie Duan, Chengyu Wang, Cen Chen, Jun Huang, Weining Qian

In this paper, we first provide a detailed theoretical and empirical analysis of the generation process of the diffusion models based on schedulers.

Image Generation

SLPerf: a Unified Framework for Benchmarking Split Learning

1 code implementation4 Apr 2023 Tianchen Zhou, Zhanyi Hu, Bingzhe Wu, Cen Chen

Data privacy concerns has made centralized training of data, which is scattered across silos, infeasible, leading to the need for collaborative learning frameworks.

Benchmarking Diversity +1

Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning

no code implementations5 Dec 2022 Mingyuan Fan, Cen Chen, Chengyu Wang, Xiaodan Li, Wenmeng Zhou

Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks.

Federated Learning Semantic Similarity +1

Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons

no code implementations13 Aug 2022 Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu, Wenzhong Guo

The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones.

backdoor defense

Transferable Adversarial Examples with Bayes Approach

1 code implementation13 Aug 2022 Mingyuan Fan, Cen Chen, Wenmeng Zhou, Yinggui Wang

In this paper, we explore the transferability of adversarial examples via the lens of Bayesian approach.

Understanding Long Programming Languages with Structure-Aware Sparse Attention

1 code implementation27 May 2022 Tingting Liu, Chengyu Wang, Cen Chen, Ming Gao, Aoying Zhou

With top-$k$ sparse attention, the most crucial attention relation can be obtained with a lower computational cost.

Case-Aware Adversarial Training

no code implementations20 Apr 2022 Mingyuan Fan, Yang Liu, Cen Chen

Specifically, the intuition stems from the fact that a very limited part of informative samples can contribute to most of model performance.

Backdoor Defense with Machine Unlearning

no code implementations24 Jan 2022 Yang Liu, Mingyuan Fan, Cen Chen, Ximeng Liu, Zhuo Ma, Li Wang, Jianfeng Ma

First, trigger pattern recovery is conducted to extract the trigger patterns infected by the victim model.

backdoor defense Machine Unlearning

Contrast R-CNN for Continual Learning in Object Detection

no code implementations11 Jul 2021 Kai Zheng, Cen Chen

In our paper, we propose a new scheme for continual learning of object detection, namely Contrast R-CNN, an approach strikes a balance between retaining the old knowledge and learning the new knowledge.

Continual Learning image-classification +5

Privacy Threats Analysis to Secure Federated Learning

no code implementations24 Jun 2021 Yuchen Li, Yifan Bao, Liyao Xiang, Junhan Liu, Cen Chen, Li Wang, Xinbing Wang

Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties.

BIG-bench Machine Learning Federated Learning +1

DSAL: Deeply Supervised Active Learning from Strong and Weak Labelers for Biomedical Image Segmentation

1 code implementation22 Jan 2021 Ziyuan Zhao, Zeng Zeng, Kaixin Xu, Cen Chen, Cuntai Guan

We use the proposed criteria to select samples for strong and weak labelers to produce oracle labels and pseudo labels simultaneously at each active learning iteration in an ensemble learning manner, which can be examined with IoMT Platform.

Active Learning Ensemble Learning +2

Towards Scalable and Privacy-Preserving Deep Neural Network via Algorithmic-Cryptographic Co-design

no code implementations17 Dec 2020 Jun Zhou, Longfei Zheng, Chaochao Chen, Yan Wang, Xiaolin Zheng, Bingzhe Wu, Cen Chen, Li Wang, Jianwei Yin

In this paper, we propose SPNN - a Scalable and Privacy-preserving deep Neural Network learning framework, from algorithmic-cryptographic co-perspective.

Privacy Preserving

Learning to Expand: Reinforced Pseudo-relevance Feedback Selection for Information-seeking Conversations

no code implementations25 Nov 2020 Haojie Pan, Cen Chen, Chengyu Wang, Minghui Qiu, Liu Yang, Feng Ji, Jun Huang

More specifically, we propose a reinforced selector to extract useful PRF terms to enhance response candidates and a BERT-based response ranker to rank the PRF-enhanced responses.

EasyTransfer -- A Simple and Scalable Deep Transfer Learning Platform for NLP Applications

2 code implementations18 Nov 2020 Minghui Qiu, Peng Li, Chengyu Wang, Hanjie Pan, Ang Wang, Cen Chen, Xianyan Jia, Yaliang Li, Jun Huang, Deng Cai, Wei Lin

The literature has witnessed the success of leveraging Pre-trained Language Models (PLMs) and Transfer Learning (TL) algorithms to a wide range of Natural Language Processing (NLP) applications, yet it is not easy to build an easy-to-use and scalable TL toolkit for this purpose.

Compiler Optimization Conversational Question Answering +1

A Theoretical Perspective on Differentially Private Federated Multi-task Learning

no code implementations14 Nov 2020 Huiwen Wu, Cen Chen, Li Wang

In the era of big data, the need to expand the amount of data through data sharing to improve model performance has become increasingly compelling.

Multi-Task Learning

Privacy-preserving Transfer Learning via Secure Maximum Mean Discrepancy

no code implementations24 Sep 2020 Bin Zhang, Cen Chen, Li Wang

The success of machine learning algorithms often relies on a large amount of high-quality data to train well-performed models.

Federated Learning Privacy Preserving +1

A Comprehensive Analysis of Information Leakage in Deep Transfer Learning

no code implementations4 Sep 2020 Cen Chen, Bingzhe Wu, Minghui Qiu, Li Wang, Jun Zhou

To the best of our knowledge, our study is the first to provide a thorough analysis of the information leakage issues in deep transfer learning methods and provide potential solutions to the issue.

Transfer Learning

A Hierarchical Deep Convolutional Neural Network and Gated Recurrent Unit Framework for Structural Damage Detection

no code implementations29 May 2020 Jianxi Yang, Likai Zhang, Cen Chen, Yangfan Li, Ren Li, Guiping Wang, Shixin Jiang, Zeng Zeng

Specifically, CNN is utilized to model the spatial relations and the short-term temporal dependencies among sensors, while the output features of CNN are fed into the GRU to learn the long-term temporal dependencies jointly.

BIG-bench Machine Learning image-classification +4

Open-Retrieval Conversational Question Answering

1 code implementation22 May 2020 Chen Qu, Liu Yang, Cen Chen, Minghui Qiu, W. Bruce Croft, Mohit Iyyer

We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers.

Conversational Question Answering Conversational Search +2

SueNes: A Weakly Supervised Approach to Evaluating Single-Document Summarization via Negative Sampling

1 code implementation NAACL 2022 Forrest Sheng Bao, Hebi Li, Ge Luo, Minghui Qiu, Yinfei Yang, Youbiao He, Cen Chen

Canonical automatic summary evaluation metrics, such as ROUGE, focus on lexical similarity which cannot well capture semantics nor linguistic quality and require a reference summary which is costly to obtain.

Abstractive Text Summarization Document Embedding +3

IART: Intent-aware Response Ranking with Transformers in Information-seeking Conversation Systems

1 code implementation3 Feb 2020 Liu Yang, Minghui Qiu, Chen Qu, Cen Chen, Jiafeng Guo, Yongfeng Zhang, W. Bruce Croft, Haiqing Chen

We also perform case studies and analysis of learned user intent and its impact on response ranking in information-seeking conversations to provide interpretation of results.

Representation Learning

Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics

no code implementations5 Oct 2019 Bingzhe Wu, Chaochao Chen, Shiwan Zhao, Cen Chen, Yuan YAO, Guangyu Sun, Li Wang, Xiaolu Zhang, Jun Zhou

Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent.

Deep Learning Generalization Bounds

Attentive History Selection for Conversational Question Answering

2 code implementations26 Aug 2019 Chen Qu, Liu Yang, Minghui Qiu, Yongfeng Zhang, Cen Chen, W. Bruce Croft, Mohit Iyyer

First, we propose a positional history answer embedding method to encode conversation history with position information using BERT in a natural way.

Conversational Question Answering Conversational Search +2

TitAnt: Online Real-time Transaction Fraud Detection in Ant Financial

no code implementations18 Jun 2019 Shaosheng Cao, Xinxing Yang, Cen Chen, Jun Zhou, Xiaolong Li, Yuan Qi

With the explosive growth of e-commerce and the booming of e-payment, detecting online transaction fraud in real time has become increasingly important to Fintech business.

Fraud Detection

A Deep Framework for Bone Age Assessment based on Finger Joint Localization

no code implementations7 May 2019 Xiaoman Zhang, Ziyuan Zhao, Cen Chen, Songyou Peng, Min Wu, Zhongyao Cheng, Singee Teo, Le Zhang, Zeng Zeng

In this study, we applied powerful deep neural network and explored a process in the forecast of skeletal bone age with the specifically combine joints images to increase the performance accuracy compared with the whole hand images.

Review Helpfulness Prediction with Embedding-Gated CNN

no code implementations29 Aug 2018 Cen Chen, Minghui Qiu, Yinfei Yang, Jun Zhou, Jun Huang, Xiaolong Li, Forrest Bao

Product reviews, in the form of texts dominantly, significantly help consumers finalize their purchasing decisions.

Prediction Sentence

Cannot find the paper you are looking for? You can Submit a new open access paper.