16 citations · 34 across the 9 of their papers we have counts for
9 papers
Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning
Zhiyang Dai, Yansong Gao, Boyu Kuang +5
Contrastive learning (CL) reduces annotation cost via auto-derived supervisory signals. Since large-scale in-house CL datasets are infeasible, reliance on third-party or internet d…
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
Hua Ma, Shang Wang, Yansong Gao +7
All current backdoor attacks on deep learning (DL) models fall under the category of a vertical class backdoor (VCB) -- class-dependent. In VCB attacks, any sample from a class act…
One-to-Multiple Clean-Label Image Camouflage (OmClic) based Backdoor Attack on Deep Learning
Guohong Wang, Hua Ma, Yansong Gao +6
Image camouflage has been utilized to create clean-label poisoned images for implanting backdoor into a DL model. But there exists a crucial limitation that one attack/poisoned ima…
TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World
Hua Ma, Yinshan Li, Yansong Gao +6
Object detection is the foundation of various critical computer-vision tasks such as segmentation, object tracking, and event detection. To train an object detector with satisfacto…
MUD-PQFed: Towards Malicious User Detection in Privacy-Preserving Quantized Federated Learning
Hua Ma, Qun Li, Yifeng Zheng +5
Federated Learning (FL), a distributed machine learning paradigm, has been adapted to mitigate privacy concerns for customers. Despite their appeal, there are various inference att…
MLMSA: Multi-Label Multi-Side-Channel-Information enabled Deep Learning Attacks on APUF Variants
Yansong Gao, Jianrong Yao, Lihui Pang +4
To improve the modeling resilience of silicon strong physical unclonable functions (PUFs), in particular, the APUFs, that yield a very large number of challenge response pairs (CRP…
Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World
Hua Ma, Yinshan Li, Yansong Gao +7
Deep learning models have been shown to be vulnerable to recent backdoor attacks. A backdoored model behaves normally for inputs containing no attacker-secretly-chosen trigger and…
NTD: Non-Transferability Enabled Backdoor Detection
Yinshan Li, Hua Ma, Zhi Zhang +6
A backdoor deep learning (DL) model behaves normally upon clean inputs but misbehaves upon trigger inputs as the backdoor attacker desires, posing severe consequences to DL model d…
Quantization Backdoors to Deep Learning Commercial Frameworks
Hua Ma, Huming Qiu, Yansong Gao +7
Currently, there is a burgeoning demand for deploying deep learning (DL) models on ubiquitous edge Internet of Things (IoT) devices attributed to their low latency and high privacy…