260 citations · 392 across the 22 of their papers we have counts for
23 papers
zkVC: Fast Zero-Knowledge Proof for Private and Verifiable Computing
Yancheng Zhang, Mengxin Zheng, Xun Chen +5
In the context of cloud computing, services are held on cloud servers, where the clients send their data to the server and obtain the results returned by server. However, the compu…
SoK: Can Fully Homomorphic Encryption Support General AI Computation? A Functional and Cost Analysis
Jiaqi Xue, Xin Xin, Wei Zhang +11
Artificial intelligence (AI) increasingly powers sensitive applications in domains such as healthcare and finance, relying on both linear operations (e.g., matrix multiplications i…
SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding
Ryan Sun, Tianyi Zhou, Xun Chen +1
Large Language Models (LLMs) have become essential in advancing natural language processing (NLP) tasks, but their sequential token generation limits inference speed. Multi-Draft S…
BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models
Jiaqi Xue, Mengxin Zheng, Yebowen Hu +3
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant information from external knowledge bases to provide more accurate, contextually i…
Rethinking and Red-Teaming Protective Perturbation in Personalized Diffusion Models
Yixin Liu, Ruoxi Chen, Xun Chen +1
Personalized diffusion models (PDMs) have become prominent for adapting pre-trained text-to-image models to generate images of specific subjects using minimal training data. Howeve…
LineBreaker: Finding Token-Inconsistency Bugs with Large Language Models
Hongbo Chen, Yifan Zhang, Xing Han +7
Token-inconsistency bugs (TIBs) involve the misuse of syntactically valid yet incorrect code tokens, such as misused variables and erroneous function invocations, which can often l…
TrustLLM: Trustworthiness in Large Language Models
Yue Huang, Lichao Sun, Haoran Wang +67
Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs prese…
Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise
Yixin Liu, Kaidi Xu, Xun Chen +1
The open source of large amounts of image data promotes the development of deep learning techniques. Along with this comes the privacy risk of these open-source image datasets bein…
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning
Mengxin Zheng, Jiaqi Xue, Xun Chen +3
Prompt tuning is one of the most effective solutions to adapting a fixed pre-trained language model (PLM) for various downstream tasks, especially with only a few input samples. Ho…
MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learning
Yixin Liu, Chenrui Fan, Yutong Dai +3
Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong hands, can fabricate misleading or harmf…
GraphCloak: Safeguarding Task-specific Knowledge within Graph-structured Data from Unauthorized Exploitation
Yixin Liu, Chenrui Fan, Xun Chen +2
As Graph Neural Networks (GNNs) become increasingly prevalent in a variety of fields, from social network analysis to protein-protein interaction studies, growing concerns have eme…
MASTERKEY: Practical Backdoor Attack Against Speaker Verification Systems
Hanqing Guo, Xun Chen, Junfeng Guo +2
Speaker Verification (SV) is widely deployed in mobile systems to authenticate legitimate users by using their voice traits. In this work, we propose a backdoor attack MASTERKEY, t…
BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks
Kai Zhang, Rong Zhou, Eashan Adhikarla +20
Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to ut…
Watermarking Text Data on Large Language Models for Dataset Copyright
Yixin Liu, Hongsheng Hu, Xun Chen +2
Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstr…
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
Mengxin Zheng, Jiaqi Xue, Zihao Wang +4
Self-supervised learning (SSL) is a prevalent approach for encoding data representations. Using a pre-trained SSL image encoder and subsequently training a downstream classifier, i…
Memory-adaptive Depth-wise Heterogeneous Federated Learning
Kai Zhang, Yutong Dai, Hongyi Wang +3
Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devi…
SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency
Junfeng Guo, Yiming Li, Xun Chen +3
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation.…
Turning a Curse into a Blessing: Enabling In-Distribution-Data-Free Backdoor Removal via Stabilized Model Inversion
Si Chen, Yi Zeng, Jiachen T. Wang +5
Many backdoor removal techniques in machine learning models require clean in-distribution data, which may not always be available due to proprietary datasets. Model inversion techn…
Efficient Federated Learning on Knowledge Graphs via Privacy-preserving Relation Embedding Aggregation
Kai Zhang, Yu Wang, Hongyi Wang +4
Federated learning (FL) can be essential in knowledge representation, reasoning, and data mining applications over multi-source knowledge graphs (KGs). A recent study FedE first pr…
Gromov-Wasserstein Discrepancy with Local Differential Privacy for Distributed Structural Graphs
Hongwei Jin, Xun Chen
Learning the similarity between structured data, especially the graphs, is one of the essential problems. Besides the approach like graph kernels, Gromov-Wasserstein (GW) distance…
You Do (Not) Belong Here: Detecting DPI Evasion Attacks with Context Learning
Shitong Zhu, Shasha Li, Zhongjie Wang +5
As Deep Packet Inspection (DPI) middleboxes become increasingly popular, a spectrum of adversarial attacks have emerged with the goal of evading such middleboxes. Many of these att…
LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy
Lichao Sun, Jianwei Qian, Xun Chen
Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that coll…
A4 : Evading Learning-based Adblockers
Shitong Zhu, Zhongjie Wang, Xun Chen +6
Efforts by online ad publishers to circumvent traditional ad blockers towards regaining fiduciary benefits, have been demonstrably successful. As a result, there have recently emer…