no code implementations • 6 May 2024 • Saket S. Chaturvedi, Lan Zhang, Wenbin Zhang, Pan He, Xiaoyong Yuan
To tackle this issue, we propose an innovative 2D-oriented backdoor attack against LiDAR-camera fusion methods for 3D object detection, named BadFusion, for preserving trigger effectiveness throughout the entire fusion process.
no code implementations • 11 Mar 2024 • Pan He, Quanyi Li, Xiaoyong Yuan, Bolei Zhou
Traffic signal control (TSC) is crucial for reducing traffic congestion that leads to smoother traffic flow, reduced idling time, and mitigated CO2 emissions.
no code implementations • 20 Jul 2023 • Shiwei Ding, Lan Zhang, Miao Pan, Xiaoyong Yuan
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).
no code implementations • 10 Jul 2023 • Gaurav Bagwe, Xiaoyong Yuan, Miao Pan, Lan Zhang
Federated continual learning (FCL) learns incremental tasks over time from confidential datasets distributed across clients.
no code implementations • 5 Dec 2022 • Hong Huang, Lan Zhang, Chaoyue Sun, Ruogu Fang, Xiaoyong Yuan, Dapeng Wu
To address these challenges, we propose FedTiny, a distributed pruning framework for federated learning that generates specialized tiny models for memory- and computing-constrained devices.
no code implementations • 21 Jul 2022 • Gaurav Bagwe, Jian Li, Xiaoyong Yuan, Lan Zhang
Moreover, to improve data efficiency and provide better generalization performance, we train the policy model with augmented data (e. g., noisy BSM and noisy surveillance images).
no code implementations • 21 Jul 2022 • Madhureeta Das, Xianhao Chen, Xiaoyong Yuan, Lan Zhang
Further, the proposed FSSDA can be effectively generalized to multi-source domain adaptation scenarios.
no code implementations • 22 Apr 2022 • Saket S. Chaturvedi, Lan Zhang, Xiaoyong Yuan
Specifically, GLA integrates an early-stage fusion via a local attention network and a late-stage fusion via a global attention network to deal with both local and global information, which automatically allocates higher weights to the modality with better detection features at the late-stage fusion to cope with the specific weather condition adaptively.
1 code implementation • 7 Feb 2022 • Xiaoyong Yuan, Lan Zhang
We first explore the impact of neural network pruning on prediction divergence, where the pruning process disproportionately affects the pruned model's behavior for members and non-members.
no code implementations • 8 Sep 2021 • Lan Zhang, Dapeng Wu, Xiaoyong Yuan
To achieve knowledge transfer across these heterogeneous on-device models, a zero-shot distillation approach is designed without any prerequisites for private on-device data, which is contrary to certain prior research based on a public dataset or a pre-trained data generator.
no code implementations • 18 Jun 2021 • Wensheng Xia, Ying Li, Lan Zhang, Zhonghai Wu, Xiaoyong Yuan
To address these challenges, we propose a novel vertical federated learning framework named Cascade Vertical Federated Learning (CVFL) to fully utilize all horizontally partitioned labels to train neural networks with privacy-preservation.
no code implementations • 21 Sep 2020 • Xiaoyong Yuan, Leah Ding, Lan Zhang, Xiaolin Li, Dapeng Wu
The experimental results reveal the severity of ES Attack: i) ES Attack successfully steals the victim model without data hurdles, and ES Attack even outperforms most existing model stealing attacks using auxiliary data in terms of model accuracy; ii) most countermeasures are ineffective in defending ES Attack; iii) ES Attack facilitates further attacks relying on the stolen model.
no code implementations • 31 Aug 2020 • Xiaoyong Yuan, Lei Ding, Malek Ben Salem, Xiaolin Li, Dapeng Wu
In this paper, we present a web event forecasting approach, DeepEvent, in enterprise web applications for better anomaly detection.
no code implementations • 8 Dec 2018 • Xiaoyong Yuan, Zheng Feng, Matthew Norton, Xiaolin Li
Utilizing recently introduced concepts from statistics and quantitative risk management, we present a general variant of Batch Normalization (BN) that offers accelerated convergence of Neural Network training compared to conventional BN.
no code implementations • 9 Jul 2018 • Xiaoyong Yuan, Pan He, Xiaolin Andy Li, Dapeng Oliver Wu
We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks (e. g., C&W attack) require manually tuning hyper-parameters and take a long time to construct an adversarial example, making it impractical to attack real-time systems; (ii) Most of the studies focus on non-sequential tasks, such as image classification, yet only a few consider sequential tasks.
1 code implementation • 19 Dec 2017 • Xiaoyong Yuan, Pan He, Qile Zhu, Xiaolin Li
In this paper, we review recent findings on adversarial examples for deep neural networks, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods.
no code implementations • 4 Dec 2017 • Ruimin Sun, Xiaoyong Yuan, Pan He, Qile Zhu, Aokun Chen, Andre Gregio, Daniela Oliveira, Xiaolin Li
Existing malware detectors on safety-critical devices have difficulties in runtime detection due to the performance overhead.