4 citations · 10 across the 15 of their papers we have counts for
16 papers
SAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data Synthesis
Chuan Li, Chengyu Wang, Cen Chen +3
Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-quality, expert-annotated traini…
Towards Robust Personalized Federated Learning: Vulnerability Assessment and Defense Co-Design
Mingyuan Fan, Cen Chen
The proliferation of IoT devices has fueled distributed edge systems to collect vast amounts of sensitive data, creating fertile ground for on-device machine learning applications.…
Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games
Mingyuan Fan, Weiguang Han, Daixin Wang +3
We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating. Wherein, LLMs receive only the ta…
When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards
Mingyuan Fan, Weiguang Han, Daixin Wang +3
Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domain…
Responsible Diffusion Models via Constraining Text Embeddings within Safe Regions
Zhiwen Li, Die Chen, Mingyuan Fan +4
The remarkable ability of diffusion models to generate high-fidelity images has led to their widespread adoption. However, concerns have also arisen regarding their potential to pr…
FedMCP: Parameter-Efficient Federated Learning with Model-Contrastive Personalization
Qianyi Zhao, Chen Qu, Cen Chen +2
With increasing concerns and regulations on data privacy, fine-tuning pretrained language models (PLMs) in federated learning (FL) has become a common paradigm for NLP tasks. Despi…
Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models
Die Chen, Zhiwen Li, Mingyuan Fan +4
Despite their remarkable image generation capabilities, text-to-image diffusion models inadvertently learn inappropriate concepts from vast and unfiltered training data, which lead…
SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images
Mingyuan Fan, Yang Liu, Cen Chen +1
Adversarial attack has garnered considerable attention due to its profound implications for the secure deployment of robots in sensitive security scenarios. To potentially push for…
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
Mingyuan Fan, Xiaodan Li, Cen Chen +2
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 inter…
On the Robustness of Split Learning against Adversarial Attacks
Mingyuan Fan, Cen Chen, Chengyu Wang +2
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., s…
On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook
Mingyuan Fan, Chengyu Wang, Cen Chen +2
Diffusion models and large language models have emerged as leading-edge generative models, revolutionizing various aspects of human life. However, the practical implementations of…
Refiner: Data Refining against Gradient Leakage Attacks in Federated Learning
Mingyuan Fan, Cen Chen, Chengyu Wang +2
Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks. Such attacks exploit clients' uploaded gradients to reconst…
Defense against Backdoor Attacks via Identifying and Purifying Bad Neurons
Mingyuan Fan, Yang Liu, Cen Chen +2
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…
Transferable Adversarial Examples with Bayes Approach
Mingyuan Fan, Cen Chen, Wenmeng Zhou +1
The vulnerability of deep neural networks (DNNs) to black-box adversarial attacks is one of the most heated topics in trustworthy AI. In such attacks, the attackers operate without…
Case-Aware Adversarial Training
Mingyuan Fan, Yang Liu, Cen Chen
The neural network (NN) becomes one of the most heated type of models in various signal processing applications. However, NNs are extremely vulnerable to adversarial examples (AEs)…
Enhance transferability of adversarial examples with model architecture
Mingyuan Fan, Wenzhong Guo, Shengxing Yu +2
Transferability of adversarial examples is of critical importance to launch black-box adversarial attacks, where attackers are only allowed to access the output of the target model…