paper-with-me

Papers

Denoising Diffusion Probabilistic Models as a Defense against Adversarial Attacks

2023-01-17 · Lars Lien Ankile, Anna Midgley, Sebastian Weisshaar

Neural Networks are infamously sensitive to small perturbations in their inputs, making them vulnerable to adversarial attacks. This project evaluates the performance of Denoising Diffusion Probabilistic Models (DDPM) as a purification technique to defend against adversarial attacks. This works by adding noise to an adversarial example before removing it through the reverse process of the diffusion model. We evaluate the approach on the PatchCamelyon data set for histopathologic scans of lymph node sections and find an improvement of the robust accuracy by up to 88\% of the original model's accuracy, constituting a considerable improvement over the vanilla model and our baselines. The project code is located at https://github.com/ankile/Adversarial-Diffusion.

📄 PDF Abstract BibTeX arXiv:2301.06871

Code (1)

ankile/adversarial-diffusion 공식 구현

Tasks

Denoising

Methods 이 논문이 사용한 방법론

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

Towards Effective and Efficient Adversarial Defense with Diffusion Models for Robust Visual Tracking

2025-05-31 · Long Xu, Peng Gao, Wen-Jia Tang, Fei Wang 외

Although deep learning-based visual tracking methods have made significant progress, they exhibit vulnerabilities when facing carefully designed adversarial attacks, which can lead to a sharp decline in tracking performa…

Adversarial DefenseDenoisingVisual Tracking

VideoPure: Diffusion-based Adversarial Purification for Video Recognition

2025-01-25 · Kaixun Jiang, Zhaoyu Chen, Jiyuan Fu, Lingyi Hong 외

Recent work indicates that video recognition models are vulnerable to adversarial examples, posing a serious security risk to downstream applications. However, current research has primarily focused on adversarial attack…

Adversarial DefenseAdversarial PurificationAdversarial RobustnessDenoising+1

Certified Robustness to Clean-Label Poisoning Using Diffusion Denoising

2024-03-18 · Sanghyun Hong, Nicholas Carlini, Alexey Kurakin

We present a certified defense to clean-label poisoning attacks under $\ell_2$-norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bounded adversarial perturbations into the …

Adversarial RobustnessDenoising

Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion

2022-11-29 · Kui Zhang, Hang Zhou, Jie Zhang, Qidong Huang 외

Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. Robust training and defend-by-denoising are typical strategies for defendin…

Autonomous DrivingDenoising

Graph Defense Diffusion Model

2025-01-20 · Xin He, Wenqi Fan, Yili Wang, Chengyi Liu 외

Graph Neural Networks (GNNs) demonstrate significant potential in various applications but remain highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods…

Denoisingmodel