4 citations · 7 across the 33 of their papers we have counts for
14 papers · 1 filter
Conjunctive Poisoning in AI Supply-Chain Applications
Nokimul Hasan Arif, Qian Lou, Mengxin Zheng
Large Language and Vision-Language Models are increasingly deployed through inference pipelines that include prompt wrappers (e.g., templates and post-processing scripts) and confi…
MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation
Yukuan Zhang, Mengxin Zheng, Qian Lou
Repository-level benchmarks for evaluating Large Language Model (LLM) code repair on Secure Multi-Party Computation (MPC) software do not yet exist, and directly transplanting gene…
SecureRouter: Encrypted Routing for Efficient Secure Inference
Yukuan Zhang, Mengxin Zheng, Qian Lou
Cryptographically secure neural network inference typically relies on secure computing techniques such as Secure Multi-Party Computation (MPC), enabling cloud servers to process cl…
RobPI: Robust Private Inference against Malicious Client
Jiaqi Xue, Mengxin Zheng, Qian Lou
The increased deployment of machine learning inference in various applications has sparked privacy concerns. In response, private inference (PI) protocols have been created to allo…
RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
Miao Lin, Feng Yu, Rui Ning +6
Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world sce…
PRO: Enabling Precise and Robust Text Watermark for Open-Source LLMs
Jiaqi Xue, Yifei Zhao, Mansour Al Ghanim +4
Text watermarking for large language models (LLMs) enables model owners to verify text origin and protect intellectual property. While watermarking methods for closed-source LLMs a…
AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs
Ruisi Zhang, Yifei Zhao, Neusha Javidnia +2
As on-device LLMs(e.g., Apple on-device Intelligence) are widely adopted to reduce network dependency, improve privacy, and enhance responsiveness, verifying the legitimacy of mode…
Securing Transformer-based AI Execution via Unified TEEs and Crypto-protected Accelerators
Jiaqi Xue, Yifei Zhao, Mengxin Zheng +3
Recent advances in Transformer models, e.g., large language models (LLMs), have brought tremendous breakthroughs in various artificial intelligence (AI) tasks, leading to their wid…
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…
TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation
Mayank Kumar, Jiaqi Xue, Mengxin Zheng +1
Fully Homomorphic Encryption over the torus (TFHE) enables computation on encrypted data without decryption, making it a cornerstone of secure and confidential computing. Despite i…
BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers
Jiaqi Xue, Qian Lou, Mengxin Zheng
Attacking fairness is crucial because compromised models can introduce biased outcomes, undermining trust and amplifying inequalities in sensitive applications like hiring, healthc…
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…
OFHE: An Electro-Optical Accelerator for Discretized TFHE
Mengxin Zheng, Cheng Chu, Qian Lou +4
This paper presents \textit{OFHE}, an electro-optical accelerator designed to process Discretized TFHE (DTFHE) operations, which encrypt multi-bit messages and support homomorphic…