12 citations · 15 across the 7 of their papers we have counts for
7 papers
SoK: Adversarial Robustness of the Variational Quantum Eigensolver via Red-Teaming
Ahmed Azaz Humdoon, Cheng Chu, Lei Jiang +2
The Variational Quantum Eigensolver (VQE) is a leading algorithm for estimating molecular ground-state energies on near-term quantum hardware, with applications spanning quantum ch…
Hardware Robustness of Sample-Based Quantum Diagonalization
Ahatesham Bhuiyan, Cheng Chu, Qian Lou +1
Sample-based Quantum Diagonalization (SQD) is a hybrid quantum-classical method that replaces variational optimization with a self-consistent recovery loop over QPU samples. Althou…
TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models
Jiaqi Xue, Mengxin Zheng, Ting Hua +4
Large Language Models (LLMs) are progressively being utilized as machine learning services and interface tools for various applications. However, the security implications of LLMs,…
Primer: Fast Private Transformer Inference on Encrypted Data
Mengxin Zheng, Qian Lou, Lei Jiang
It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g., fully homomorphic encrypt…
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…
CryptoLight: An Electro-Optical Accelerator for Fully Homomorphic Encryption
Mengxin Zheng, Qian Lou, Fan Chen +2
Fully homomorphic encryption (FHE) protects data privacy in cloud computing by enabling computations to directly occur on ciphertexts. To improve the time-consuming FHE operations,…
TrojViT: Trojan Insertion in Vision Transformers
Mengxin Zheng, Qian Lou, Lei Jiang
Vision Transformers (ViTs) have demonstrated the state-of-the-art performance in various vision-related tasks. The success of ViTs motivates adversaries to perform backdoor attacks…