Binbin Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Binbin Liu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Jihong Zhu
Department of Precision Instrument, Tsinghua University, Beijing 100084, China
3 shared publications - Jinlai Zhang
Changsha University of Science and Technology
3 shared publications Bo Ouyang
Department of Computer Science and Technology, Tsinghua University, Beijing, China
1 shared publicationHouqing Wang
Department of Precision Instrument, Tsinghua University, Beijing, China
1 shared publicationLyujie Chen
1 shared publicationMinchi Kuang
Department of Precision Instrument, Tsinghua University, Beijing, China
1 shared publication
Latest Publications
- 22 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 3267-3276
The Art of Defense: Letting Networks Fool the Attacker
3D perception of objects is critical for many real-world applications, such as autonomous cars and robots. Among them, most state-of-the-art (SOTA) 3D perception systems are based on deep learning models. Recently, the research community found that 3D object classifiers on point cloud based on deep learning are easily fooled by adversarial point cloud craft by attackers. To overcome this, adversarial defenses are considered the most effective ways to improve the robustness of deep learning models, and most adversarial defenses on point cloud are focused on input transformation. However, all previous defense methods decrease the natural accuracy, and the nature of the point cloud classifiers itself has been overlooked. To this end, in this paper, we propose a novel adversarial defense for 3D point cloud classifiers that makes full use of the nature of the point cloud classifiers. Due to the disorder of point cloud, all point cloud classifiers have the property of permutation invariant to the input point cloud. Based on this nature, we design invariant transformations defense (IT-Defense). We show that, even after accounting for obfuscated gradients, our IT-Defense is a resilient defense against SOTA 3D attacks. Moreover, IT-Defense does not hurt clean accuracy compared to previous SOTA 3D defenses. Our code will be available at: https://github.com/cuge1995/IT-Defense.
- 22 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 3267-3276
The Art of Defense: Letting Networks Fool the Attacker
3D perception of objects is critical for many real-world applications, such as autonomous cars and robots. Among them, most state-of-the-art (SOTA) 3D perception systems are based on deep learning models. Recently, the research community found that 3D object classifiers on point cloud based on deep learning are easily fooled by adversarial point cloud craft by attackers. To overcome this, adversarial defenses are considered the most effective ways to improve the robustness of deep learning models, and most adversarial defenses on point cloud are focused on input transformation. However, all previous defense methods decrease the natural accuracy, and the nature of the point cloud classifiers itself has been overlooked. To this end, in this paper, we propose a novel adversarial defense for 3D point cloud classifiers that makes full use of the nature of the point cloud classifiers. Due to the disorder of point cloud, all point cloud classifiers have the property of permutation invariant to the input point cloud. Based on this nature, we design invariant transformations defense (IT-Defense). We show that, even after accounting for obfuscated gradients, our IT-Defense is a resilient defense against SOTA 3D attacks. Moreover, IT-Defense does not hurt clean accuracy compared to previous SOTA 3D defenses. Our code will be available at: https://github.com/cuge1995/IT-Defense.
- Open Access
- 2 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 50974-50984
Boosting 3D Adversarial Attacks With Attacking on Frequency
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks in the image domain. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transferability and are easy to defend. To address these problems, in this paper we propose a strong point cloud attack method named AOF which pays more attention to the low-frequency component of point clouds. We combine the losses from point cloud and its low-frequency component to craft adversarial samples and focus on the low-frequency component of point cloud in the process of optimization. Extensive experiments validate that AOF can improve the transferability significantly compared to state-of-the-art (SOTA) attacks, and is more robust to state-of-the-art 3D defense methods. Otherwise, compared to adversarial point clouds generated by other adversarial attack methods, adversarial point clouds obtained by AOF contain more deformation than outlier. Code is available at: https://github.com/code-roamer/AOF .
- 2 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 50974-50984
Open AccessBoosting 3D Adversarial Attacks With Attacking on Frequency
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks in the image domain. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transferability and are easy to defend. To address these problems, in this paper we propose a strong point cloud attack method named AOF which pays more attention to the low-frequency component of point clouds. We combine the losses from point cloud and its low-frequency component to craft adversarial samples and focus on the low-frequency component of point cloud in the process of optimization. Extensive experiments validate that AOF can improve the transferability significantly compared to state-of-the-art (SOTA) attacks, and is more robust to state-of-the-art 3D defense methods. Otherwise, compared to adversarial point clouds generated by other adversarial attack methods, adversarial point clouds obtained by AOF contain more deformation than outlier. Code is available at: https://github.com/code-roamer/AOF .
- Open Access
Boosting 3D Adversarial Attacks with Attacking On Frequency
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transferability and are easy to defend. To address these problems, in this paper we propose a novel point cloud attack (dubbed AOF) that pays more attention on the low-frequency component of point clouds. We combine the losses from point cloud and its low-frequency component to craft adversarial samples. Extensive experiments validate that AOF can improve the transferability significantly compared to state-of-the-art (SOTA) attacks, and is more robust to SOTA 3D defense methods. Otherwise, compared to clean point clouds, adversarial point clouds obtained by AOF contain more deformation than outlier.
Open AccessBoosting 3D Adversarial Attacks with Attacking On Frequency
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest. However, adversarial point clouds obtained by previous methods show weak transferability and are easy to defend. To address these problems, in this paper we propose a novel point cloud attack (dubbed AOF) that pays more attention on the low-frequency component of point clouds. We combine the losses from point cloud and its low-frequency component to craft adversarial samples. Extensive experiments validate that AOF can improve the transferability significantly compared to state-of-the-art (SOTA) attacks, and is more robust to SOTA 3D defense methods. Otherwise, compared to clean point clouds, adversarial point clouds obtained by AOF contain more deformation than outlier.
- Open Access
- 1 September 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2037 (1) , 012126
Network Security Threat Situation Recognition Based on Attack and Defense Game Model
- 1 September 2021
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2037 (1) , 012126
Open AccessNetwork Security Threat Situation Recognition Based on Attack and Defense Game Model