Hongwei Li

Engineering searchable encryption of mobile cloud networks: when QoE meets QoP

2015 · IEEE Wireless Communications

Mobile cloud computing can effectively address the resource limitations of mobile devices, and is therefore essential to enable extensive resource consuming mobile computing and communication applications. Of all the mobile cloud computing applications, data outsourcing, …

A Flexible Poisoning Attack Against Machine Learning

2019

Recent years have witnessed tremendous academic efforts and industry growth in machine learning. The security of machine learning has become increasingly prominent. Poisoning attack is one of the most relevant security threats to machine learning …

Quantum algorithms for the Goldreich-Levin learning problem

2019 · arXiv (Cornell University)

The Goldreich-Levin algorithm was originally proposed for a cryptographic purpose and then applied to learning. The algorithm is to find some larger Walsh coefficients of an $n$ variable Boolean function. Roughly speaking, it takes a …

Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns

2020 · arXiv (Cornell University)

In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e.g. a new centreor a new …

Secure and Verifiable Inference in Deep Neural Networks

2020 · Annual Computer Security Applications Conference

Outsourced inference service has enormously promoted the popularity of deep learning, and helped users to customize a range of personalized applications. However, it also entails a variety of security and privacy issues brought by untrusted …

Privacy-Preserving Byzantine-Robust Federated Learning via Blockchain Systems

2022 · IEEE Transactions on Information Forensics and Security

Federated learning enables clients to train a machine learning model jointly without sharing their local data. However, due to the centrality of federated learning framework and the untrustworthiness of clients, traditional federated learning solutions are …

Incremental Learning, Incremental Backdoor Threats

2022 · IEEE Transactions on Dependable and Secure Computing

Class incremental learning from a pre-trained DNN model is gaining lots of popularity. Unfortunately, the pre-trained model also introduces a new attack vector, which enables an adversary to inject a backdoor into it and further …

Reference-frame-independent quantum key distribution with two-way classical communication

2024 · Chinese Physics B

Abstract The data post-processing scheme based on two-way classical communication (TWCC) can improve the tolerable bit error rate and extend the maximal transmission distance when used in a quantum key distribution (QKD) system. In this …