Defensive Patches for Robust Recognition in the Physical World
Jiakai Wang, Zixin Yin, Pengfei Hu, Renshuai Tao, Haotong Qin, Xianglong Liu*, Dacheng Tao, Aishan Liu
IEEE CVPR, 2022
@inproceedings{Wang:CVPR22,
author = {Jiakai Wang and Zixin Yin and Pengfei Hu and Renshuai Tao and Haotong Qin and Xianglong Liu and Dacheng Tao and Aishan Liu},
title = {Defensive Patches for Robust Recognition in the Physical World},
booktitle = {IEEE CVPR},
year = {2022},
}
Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World
Jiakai Wang, Aishan Liu, Zixin Yin, Shunchang Liu, Shiyu Tang, Xianglong Liu*
IEEE CVPR (oral), 2021
@inproceedings{Wang:cvpr21,
author = {Jiakai Wang and Aishan Liu and Zixin Yin and Shunchang Liu and Shiyu Tang and Xianglong Liu},
title = {Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World},
booktitle = {IEEE CVPR},
year = {2021},
}
Bias-based Universal Adversarial Patch Attack for Automatic Check-out
Aishan Liu, Jiakai Wang, Xianglong Liu*, Bowen Cao, Chongzhi Zhang, Hang Yu.
ECCV, 2020
@inproceedings{Liu:eccv20_bias,
author = {Aishan Liu and Jiakai Wang and Xianglong Liu and Bowen Cao and Chongzhi Zhang and Hang Yu},
title = {Bias-based Universal Adversarial Patch Attack for Automatic Check-out},
booktitle = {ECCV},
year = {2020},
}
Spatiotemporal Attacks for Embodied Agents
Aishan Liu, Tairan Huang, Xianglong Liu, Yitao Xu, Yuqing Ma, Xinyun Chen, Stephen Maybank, Dacheng Tao
ECCV, 2020
@inproceedings{Liu:eccv20_spatiotemporal,
author = {Aishan Liu and Tairan Huang and Xianglong Liu and Yitao Xu and Yuqing Ma and Xinyun Chen and Stephen Maybank and Dacheng Tao},
title = {Spatiotemporal Attacks for Embodied Agents},
booktitle = {ECCV},
year = {2020},
}
Perceptual-Sensitive GAN for Generating Adversarial Patches
Aishan Liu, Xianglong Liu*, Jiaxin Fan, Yuqing Ma, Anlan Zhang, Huiyuan Xie, Dacheng Tao
AAAI, 2019
@inproceedings{Liu:aaai19,
author = {Aishan Liu and Xianglong Liu and Jiaxin Fan and Yuqing Ma and Anlan Zhang and Huiyuan Xie and Dacheng Tao},
title = {Perceptual-Sensitive GAN for Generating Adversarial Patches},
booktitle = {AAAI},
year = {2019},
}
重明 (AISafety)
面向人工智能安全的评测评估平台“重明”，集成算法库、模型库、指标库、数据库等资源，包含20余种对抗样本攻击、19种噪声攻击、5大类30余种评测算法、覆盖60余种典型的计算机视觉模型以及30余种典型的自然语言处理模型；可支持一站式评测流程，以及可解释报生成。集成沙盒3D仿真验证环境集。核心代码开源并获得
首届OpenI启智社区优秀开源项目。该平台已集成于工信部人工智能算法检验检测平台并服务揭榜评测，获得科技创新2030—“新一代人工智能”重大专项支持，已开展15家人工智能领头企业的智能算法及系统的评测工作，推动人工智能产业生态的健康发展。
RobustART
RobustART is the first comprehensive Robustness investigation benchmark on large-scale dataset ImageNet regarding ARchitectural design (49 human-designed off-the-shelf architectures and 1200+ neural architecture searched networks) and Training techniques (10+ general ones e.g., extra training data, etc) towards diverse noises (adversarial, natural, and system noises). Our benchmark (including open-source toolkit, pre-trained model zoo, datasets, and analyses): (1) presents an open-source platform for conducting comprehensive evaluation on diverse robustness types; (2) provides a variety of pre-trained models with different training techniques to facilitate robustness evaluation; (3) proposes a new view to better understand the mechanism towards designing robust DNN architectures, backed up by the analysis. We will continuously contribute to building this ecosystem for the community.
