Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Xiaojun Jia

Xiaojun Jia

Context-Aware Robust Fine-Tuning

Nov 29, 2022
Xiaofeng Mao, Yuefeng Chen, Xiaojun Jia, Rong Zhang, Hui Xue, Zhao Li

Access Paper or Ask Questions

A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

Sep 16, 2022
Siyuan Liang, Longkang Li, Yanbo Fan, Xiaojun Jia, Jingzhi Li, Baoyuan Wu, Xiaochun Cao

Figure 1 for A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

Figure 2 for A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

Figure 3 for A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

Figure 4 for A Large-scale Multiple-objective Method for Black-box Attack against Object Detection

* 14 pages, 5 figures, ECCV2022

Access Paper or Ask Questions

MOVE: Effective and Harmless Ownership Verification via Embedded External Features

Aug 04, 2022
Yiming Li, Linghui Zhu, Xiaojun Jia, Yang Bai, Yong Jiang, Shu-Tao Xia, Xiaochun Cao

Figure 1 for MOVE: Effective and Harmless Ownership Verification via Embedded External Features

Figure 2 for MOVE: Effective and Harmless Ownership Verification via Embedded External Features

Figure 3 for MOVE: Effective and Harmless Ownership Verification via Embedded External Features

Figure 4 for MOVE: Effective and Harmless Ownership Verification via Embedded External Features

* 15 pages. The journal extension of our conference paper in AAAI 2022 (https://ojs.aaai.org/index.php/AAAI/article/view/20036). arXiv admin note: substantial text overlap with arXiv:2112.03476

Access Paper or Ask Questions

Prior-Guided Adversarial Initialization for Fast Adversarial Training

Jul 18, 2022
Xiaojun Jia, Yong Zhang, Xingxing Wei, Baoyuan Wu, Ke Ma, Jue Wang, Xiaochun Cao

Figure 1 for Prior-Guided Adversarial Initialization for Fast Adversarial Training

Figure 2 for Prior-Guided Adversarial Initialization for Fast Adversarial Training

Figure 3 for Prior-Guided Adversarial Initialization for Fast Adversarial Training

Figure 4 for Prior-Guided Adversarial Initialization for Fast Adversarial Training

* ECCV 2022
* ECCV 2022

Access Paper or Ask Questions

LAS-AT: Adversarial Training with Learnable Attack Strategy

Mar 13, 2022
Xiaojun Jia, Yong Zhang, Baoyuan Wu, Ke Ma, Jue Wang, Xiaochun Cao

Figure 1 for LAS-AT: Adversarial Training with Learnable Attack Strategy

Figure 2 for LAS-AT: Adversarial Training with Learnable Attack Strategy

Figure 3 for LAS-AT: Adversarial Training with Learnable Attack Strategy

Figure 4 for LAS-AT: Adversarial Training with Learnable Attack Strategy

* CVPR 2022

Access Paper or Ask Questions

Defending against Model Stealing via Verifying Embedded External Features

Dec 07, 2021
Yiming Li, Linghui Zhu, Xiaojun Jia, Yong Jiang, Shu-Tao Xia, Xiaochun Cao

Figure 1 for Defending against Model Stealing via Verifying Embedded External Features

Figure 2 for Defending against Model Stealing via Verifying Embedded External Features

Figure 3 for Defending against Model Stealing via Verifying Embedded External Features

Figure 4 for Defending against Model Stealing via Verifying Embedded External Features

* This work is accepted by the AAAI 2022. The first two authors contributed equally to this work. 11 pages

Access Paper or Ask Questions