research
∙
06/12/2023
TrojPrompt: A Black-box Trojan Attack on Pre-trained Language Models
Prompt learning has been proven to be highly effective in improving pre-...
share
research
∙
03/23/2023
Primer: Fast Private Transformer Inference on Encrypted Data
It is increasingly important to enable privacy-preserving inference for ...
research
∙
03/16/2023
SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
Self-supervised learning (SSL) is a commonly used approach to learning a...
research
∙
03/15/2023
vFHE: Verifiable Fully Homomorphic Encryption with Blind Hash
Fully homomorphic encryption (FHE) is a powerful encryption technique th...
research
∙
03/03/2023
TrojText: Test-time Invisible Textual Trojan Insertion
In Natural Language Processing (NLP), intelligent neuron models can be s...
research
∙
11/24/2022
CryptoLight: An Electro-Optical Accelerator for Fully Homomorphic Encryption
Fully homomorphic encryption (FHE) protects data privacy in cloud comput...
research
∙
11/20/2022
ESTAS: Effective and Stable Trojan Attacks in Self-supervised Encoders with One Target Unlabelled Sample
Emerging self-supervised learning (SSL) has become a popular image repre...
research
∙
09/20/2022
Audit and Improve Robustness of Private Neural Networks on Encrypted Data
Performing neural network inference on encrypted data without decryption...
research
∙
08/27/2022
TrojViT: Trojan Insertion in Vision Transformers
Vision Transformers (ViTs) have demonstrated the state-of-the-art perfor...
research
∙
06/30/2022
Language model compression with weighted low-rank factorization
Factorizing a large matrix into small matrices is a popular strategy for...
research
∙
02/17/2022
MATCHA: A Fast and Energy-Efficient Accelerator for Fully Homomorphic Encryption over the Torus
Fully Homomorphic Encryption over the Torus (TFHE) allows arbitrary comp...
research
∙
12/30/2021
Automatic Mixed-Precision Quantization Search of BERT
Pre-trained language models such as BERT have shown remarkable effective...
research
∙
05/31/2021
HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture
Recently Homomorphic Encryption (HE) is used to implement Privacy-Preser...
research
∙
04/06/2021
How to Accelerate Capsule Convolutions in Capsule Networks
How to improve the efficiency of routing procedures in CapsNets has been...
research
∙
10/22/2020
CryptoGRU: Low Latency Privacy-Preserving Text Analysis With GRU
Billions of text analysis requests containing private emails, personal t...
research
∙
08/04/2020
Helix: Algorithm/Architecture Co-design for Accelerating Nanopore Genome Base-calling
Nanopore genome sequencing is the key to enabling personalized medicine,...
research
∙
06/07/2020
AutoPrivacy: Automated Layer-wise Parameter Selection for Secure Neural Network Inference
Hybrid Privacy-Preserving Neural Network (HPPNN) implementing linear lay...
research
∙
11/16/2019
Glyph: Fast and Accurately Training Deep Neural Networks on Encrypted Data
Big data is one of the cornerstones to enabling and training deep neural...
research
∙
06/01/2019
SHE: A Fast and Accurate Privacy-Preserving Deep Neural Network Via Leveled TFHE and Logarithmic Data Representation
Homomorphic Encryption (HE) is one of the most promising security soluti...
research
∙
02/15/2019