98 citations · 474 across the 39 of their papers we have counts for
8 papers · 1 filter
FastFHE: Packing-Scalable and Depthwise-Separable CNN Inference Over FHE
Wenbo Song, Xinxin Fan, Quanliang Jing +5
The deep learning (DL) has been penetrating daily life in many domains, how to keep the DL model inference secure and sample privacy in an encrypted environment has become an urgen…
Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control
Ka-Ho Chow, Wenqi Wei, Lei Yu
Natural language processing (NLP) has received unprecedented attention. While advancements in NLP models have led to extensive research into their backdoor vulnerabilities, the pot…
Few-shot Multi-domain Knowledge Rearming for Context-aware Defence against Advanced Persistent Threats
Gaolei Li, Yuanyuan Zhao, Wenqi Wei +1
Advanced persistent threats (APTs) have novel features such as multi-stage penetration, highly-tailored intention, and evasive tactics. APTs defense requires fusing multi-dimension…
STDLens: Model Hijacking-Resilient Federated Learning for Object Detection
Ka-Ho Chow, Ling Liu, Wenqi Wei +2
Federated Learning (FL) has been gaining popularity as a collaborative learning framework to train deep learning-based object detection models over a distributed population of clie…
Understanding Object Detection Through An Adversarial Lens
Ka-Ho Chow, Ling Liu, Mehmet Emre Gursoy +3
Deep neural networks based object detection models have revolutionized computer vision and fueled the development of a wide range of visual recognition applications. However, recen…
Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerability
Stacey Truex, Ling Liu, Mehmet Emre Gursoy +2
Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evalu…
Secure and Utility-Aware Data Collection with Condensed Local Differential Privacy
Mehmet Emre Gursoy, Acar Tamersoy, Stacey Truex +2
Local Differential Privacy (LDP) is popularly used in practice for privacy-preserving data collection. Although existing LDP protocols offer high utility for large user populations…
Towards Demystifying Membership Inference Attacks
Stacey Truex, Ling Liu, Mehmet Emre Gursoy +2
Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service…