Adversarial Example Detection Using Latent Neighborhood Graph-Reference-Cited by-同舟云学术

Adversarial Example Detection Using Latent Neighborhood Graph

Published:2021-10 Issue: Volume: Page:
ISSN:
Container-title:2021 IEEE/CVF International Conference on Computer Vision (ICCV)
language:
Short-container-title:

Author:

Abusnaina Ahmed¹,Wu Yuhang²,Arora Sunpreet²,Wang Yizhen²,Wang Fei²,Yang Hao²,Mohaisen David¹

Affiliation:

1. University of Central Florida

2. Visa Research

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9709627/9709628/09710861.pdf?arnumber=9710861

Reference49 articles.

1. Adversarial and clean data are not twins;gong;CoRR,2017

2. Characterizing adversarial subspaces using local intrinsic dimensionality;ma;6th International Conference on Learning Representations ICLR,2018

3. A new defense against adversarial images: Turning a weakness into a strength;hu;Advances in Neural Information Processing Systems 32 Annual Conference on Neural Information Processing Systems NeurIPS,2019

4. Detecting adversarial samples from artifacts;feinman;CoRR,2017

5. Graph attention networks;velickovic;CoRR,2017

Cited by 30 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Defense against Adversarial Attacks in Image Recognition Based on Multilayer Filters;Applied Sciences;2024-09-10

2. Adversarial self-training for robustness and generalization;Pattern Recognition Letters;2024-09

3. A composite manifold learning approach with traditional methods for gradient-based and patch-based adversarial attack detection;Multimedia Tools and Applications;2024-07-16

4. A Secure GNN Training Framework for Partially Observable Graph;Electronics;2024-07-11

5. GGT: Graph-guided testing for adversarial sample detection of deep neural network;Computers & Security;2024-05