paper-with-me

Papers

PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition

2022-08-21 · Jiachen Sun, Weili Nie, Zhiding Yu, Z. Morley Mao, Chaowei Xiao

3D Point cloud is becoming a critical data representation in many real-world applications like autonomous driving, robotics, and medical imaging. Although the success of deep learning further accelerates the adoption of 3D point clouds in the physical world, deep learning is notorious for its vulnerability to adversarial attacks. In this work, we first identify that the state-of-the-art empirical defense, adversarial training, has a major limitation in applying to 3D point cloud models due to gradient obfuscation. We further propose PointDP, a purification strategy that leverages diffusion models to defend against 3D adversarial attacks. We extensively evaluate PointDP on six representative 3D point cloud architectures, and leverage 10+ strong and adaptive attacks to demonstrate its lower-bound robustness. Our evaluation shows that PointDP achieves significantly better robustness than state-of-the-art purification methods under strong attacks. Results of certified defenses on randomized smoothing combined with PointDP will be included in the near future.

📄 PDF Abstract BibTeX arXiv:2208.09801

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingDeep Learning

Methods 이 논문이 사용한 방법론

Randomized Smoothing 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

PCLD: Point Cloud Layerwise Diffusion for Adversarial Purification

2024-03-11 · Mert Gulsen, Batuhan Cengiz, Yusuf H. Sahin, Gozde Unal

Point clouds are extensively employed in a variety of real-world applications such as robotics, autonomous driving and augmented reality. Despite the recent success of point cloud neural networks, especially for safety-c…

Adversarial PurificationAutonomous DrivingDenoising

Purify++: Improving Diffusion-Purification with Advanced Diffusion Models and Control of Randomness

2023-10-28 · Boya Zhang, Weijian Luo, Zhihua Zhang

Adversarial attacks can mislead neural network classifiers. The defense against adversarial attacks is important for AI safety. Adversarial purification is a family of approaches that defend adversarial attacks with suit…

Adversarial Purification

Robust Evaluation of Diffusion-Based Adversarial Purification

2023-03-16 · ICCV 2023 1 · Minjong Lee, Dongwoo Kim

We question the current evaluation practice on diffusion-based purification methods. Diffusion-based purification methods aim to remove adversarial effects from an input data point at test time. The approach gains increa…

Adversarial Purification

Text Adversarial Purification as Defense against Adversarial Attacks

2022-03-27 · Linyang Li, Demin Song, Xipeng Qiu

Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purification aims to remove the adversarial pe…

Adversarial AttackAdversarial DefenseAdversarial Purification

ADBM: Adversarial diffusion bridge model for reliable adversarial purification

2024-08-01 · Xiao Li, Wenxuan Sun, Huanran Chen, Qiongxiu Li 외

Recently Diffusion-based Purification (DiffPure) has been recognized as an effective defense method against adversarial examples. However, we find DiffPure which directly employs the original pre-trained diffusion models…

Adversarial Purification