English
Related papers

Related papers: Guided Diffusion Model for Adversarial Purificatio…

200 papers

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 perturbations…

Computation and Language · Computer Science 2023-05-04 Linyang Li , Demin Song , Xipeng Qiu

Despite significant advances in the area, adversarial robustness remains a critical challenge in systems employing machine learning models. The removal of adversarial perturbations at inference time, known as adversarial purification, has…

Machine Learning · Computer Science 2026-03-31 Elias Collaert , Abel Rodríguez , Sander Joos , Lieven Desmet , Vera Rimmer

Adversarial purification using generative models demonstrates strong adversarial defense performance. These methods are classifier and attack-agnostic, making them versatile but often computationally intensive. Recent strides in diffusion…

Machine Learning · Computer Science 2026-04-10 Himanshu Singh , A V Subramanyam

Neural networks are known to be susceptible to adversarial samples: small variations of natural examples crafted to deliberately mislead the models. While they can be easily generated using gradient-based techniques in digital and physical…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Haotian Xue , Alexandre Araujo , Bin Hu , Yongxin Chen

Adversarial evasion attacks pose significant threats to graph learning, with lines of studies that have improved the robustness of Graph Neural Networks (GNNs). However, existing works rely on priors about clean graphs or attacking…

Machine Learning · Computer Science 2025-02-10 Jiayi Luo , Qingyun Sun , Haonan Yuan , Xingcheng Fu , Jianxin Li

Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training, whose effectiveness is often later reduced by unseen…

Machine Learning · Computer Science 2023-05-18 Thomas Altstidl , David Dobre , Björn Eskofier , Gauthier Gidel , Leo Schwinn

Deep learning models have been widely used in commercial acoustic systems in recent years. However, adversarial audio examples can cause abnormal behaviors for those acoustic systems, while being hard for humans to perceive. Various…

Sound · Computer Science 2023-03-06 Shutong Wu , Jiongxiao Wang , Wei Ping , Weili Nie , Chaowei Xiao

The presence of adversarial examples poses a significant threat to deep learning models and their applications. Existing defense methods provide certain resilience against adversarial examples, but often suffer from decreased accuracy and…

Cryptography and Security · Computer Science 2023-11-27 Jiahao Chen , Diqun Yan , Li Dong

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 for adversarial…

Machine Learning · Computer Science 2025-03-20 Xiao Li , Wenxuan Sun , Huanran Chen , Qiongxiu Li , Yining Liu , Yingzhe He , Jie Shi , Xiaolin Hu

This paper presents a novel reconstruction method that leverages Diffusion Models to protect machine learning classifiers against adversarial attacks, all without requiring any modifications to the classifiers themselves. The susceptibility…

Machine Learning · Computer Science 2023-09-08 Hondamunige Prasanna Silva , Lorenzo Seidenari , Alberto Del Bimbo

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…

Computation and Language · Computer Science 2025-05-20 Zhenhao Li , Huichi Zhou , Marek Rei , Lucia Specia

Diffusion models like Stable Diffusion have become prominent in visual synthesis tasks due to their powerful customization capabilities, which also introduce significant security risks, including deepfakes and copyright infringement. In…

Computer Vision and Pattern Recognition · Computer Science 2025-09-22 Wenkui Yang , Jie Cao , Junxian Duan , Ran He

While foundation models demonstrate impressive performance across various tasks, they remain vulnerable to adversarial inputs. Current research explores various approaches to enhance model robustness, with Diffusion Denoised Smoothing…

Machine Learning · Computer Science 2025-05-22 Yury Belousov , Brian Pulfer , Vitaliy Kinakh , Slava Voloshynovskiy

The improvement of language model robustness, including successful defense against adversarial attacks, remains an open problem. In computer vision settings, the stochastic noising and de-noising process provided by diffusion models has…

Machine Learning · Computer Science 2024-06-21 Harrison Gietz , Jugal Kalita

Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learning attacks where minor input perturbations can significantly…

Cryptography and Security · Computer Science 2024-09-04 Hossein Khalili , Seongbin Park , Vincent Li , Brandan Bright , Ali Payani , Ramana Rao Kompella , Nader Sehatbakhsh

Black-box query-based attacks constitute significant threats to Machine Learning as a Service (MLaaS) systems since they can generate adversarial examples without accessing the target model's architecture and parameters. Traditional defense…

Cryptography and Security · Computer Science 2025-06-27 Ping Guo , Xiang Li , Zhiyuan Yang , Xi Lin , Qingchuan Zhao , Qingfu Zhang

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 attacks, with limited work…

Computer Vision and Pattern Recognition · Computer Science 2025-01-28 Kaixun Jiang , Zhaoyu Chen , Jiyuan Fu , Lingyi Hong , Jinglun Li , Wenqiang Zhang

Deep learning models are known to be vulnerable to adversarial attacks by injecting sophisticated designed perturbations to input data. Training-time defenses still exhibit a significant performance gap between natural accuracy and robust…

Machine Learning · Computer Science 2025-05-20 Cheng-Han Yeh , Kuanchun Yu , Chun-Shien Lu

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 training data to…

Cryptography and Security · Computer Science 2025-06-03 Sanghyun Hong , Nicholas Carlini , Alexey Kurakin

Graph Neural Networks (GNNs) are highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods attempt to address this issue by filtering attacked graphs. However, they struggle…

Machine Learning · Computer Science 2026-04-13 Xin He , Wenqi Fan , Yili Wang , Chengyi Liu , Rui Miao , Xin Juan , Xin Wang