13 citations · 58 across the 13 of their papers we have counts for
13 papers
BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection
Saket S. Chaturvedi, Lan Zhang, Wenbin Zhang +2
3D object detection plays an important role in autonomous driving; however, its vulnerability to backdoor attacks has become evident. By injecting ''triggers'' to poison the traini…
PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attacks
Shiwei Ding, Lan Zhang, Miao Pan +1
Collaborative inference has been a promising solution to enable resource-constrained edge devices to perform inference using state-of-the-art deep neural networks (DNNs). In collab…
Fed-CPrompt: Contrastive Prompt for Rehearsal-Free Federated Continual Learning
Gaurav Bagwe, Xiaoyong Yuan, Miao Pan +1
Federated continual learning (FCL) learns incremental tasks over time from confidential datasets distributed across clients. This paper focuses on rehearsal-free FCL, which has sev…
Distributed Pruning Towards Tiny Neural Networks in Federated Learning
Hong Huang, Lan Zhang, Chaoyue Sun +3
Neural network pruning is an essential technique for reducing the size and complexity of deep neural networks, enabling large-scale models on devices with limited resources. Howeve…
Federated Semi-Supervised Domain Adaptation via Knowledge Transfer
Madhureeta Das, Xianhao Chen, Xiaoyong Yuan +1
Given the rapidly changing machine learning environments and expensive data labeling, semi-supervised domain adaptation (SSDA) is imperative when the labeled data from the source d…
Towards Robust On-Ramp Merging via Augmented Multimodal Reinforcement Learning
Gaurav Bagwe, Jian Li, Xiaoyong Yuan +1
Despite the success of AI-enabled onboard perception, on-ramp merging has been one of the main challenges for autonomous driving. Due to limited sensing range of onboard sensors, a…
Residue-based Label Protection Mechanisms in Vertical Logistic Regression
Juntao Tan, Lan Zhang, Yang Liu +2
Federated learning (FL) enables distributed participants to collaboratively learn a global model without revealing their private data to each other. Recently, vertical FL, where th…
Pay "Attention" to Adverse Weather: Weather-aware Attention-based Object Detection
Saket S. Chaturvedi, Lan Zhang, Xiaoyong Yuan
Despite the recent advances of deep neural networks, object detection for adverse weather remains challenging due to the poor perception of some sensors in adverse weather. Instead…
Membership Inference Attacks and Defenses in Neural Network Pruning
Xiaoyong Yuan, Lan Zhang
Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most exist…
FedZKT: Zero-Shot Knowledge Transfer towards Resource-Constrained Federated Learning with Heterogeneous On-Device Models
Lan Zhang, Dapeng Wu, Xiaoyong Yuan
Federated learning enables multiple distributed devices to collaboratively learn a shared prediction model without centralizing their on-device data. Most of the current algorithms…
Adaptive perturbation adversarial training: based on reinforcement learning
Zhishen Nie, Ying Lin, Sp Ren +1
Adversarial training has become the primary method to defend against adversarial samples. However, it is hard to practically apply due to many shortcomings. One of the shortcomings…
A Vertical Federated Learning Framework for Horizontally Partitioned Labels
Wensheng Xia, Ying Li, Lan Zhang +2
Vertical federated learning is a collaborative machine learning framework to train deep leaning models on vertically partitioned data with privacy-preservation. It attracts much at…
ES Attack: Model Stealing against Deep Neural Networks without Data Hurdles
Xiaoyong Yuan, Leah Ding, Lan Zhang +2
Deep neural networks (DNNs) have become the essential components for various commercialized machine learning services, such as Machine Learning as a Service (MLaaS). Recent studies…