English
Related papers

Related papers: Why Do Adversarial Attacks Transfer? Explaining Tr…

200 papers

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Cryptography and Security · Computer Science 2023-06-30 Nils Lukas , Florian Kerschbaum

The transferability of adversarial examples across deep neural networks (DNNs) is the crux of many black-box attacks. Many prior efforts have been devoted to improving the transferability via increasing the diversity in inputs of some…

Machine Learning · Computer Science 2023-07-20 Qizhang Li , Yiwen Guo , Wangmeng Zuo , Hao Chen

In the transfer-based adversarial attacks, adversarial examples are only generated by the surrogate models and achieve effective perturbation in the victim models. Although considerable efforts have been developed on improving the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-14 Xiangyuan Yang , Jie Lin , Hanlin Zhang , Xinyu Yang , Peng Zhao

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of…

Machine Learning · Computer Science 2020-02-21 Yizhen Wang , Somesh Jha , Kamalika Chaudhuri

In this paper, we present the first detailed analysis of how training hyperparameters -- such as learning rate, weight decay, momentum, and batch size -- influence robustness against both transfer-based and query-based attacks. Supported by…

Machine Learning · Computer Science 2025-12-19 Pascal Zimmer , Ghassan Karame

Transfer learning, in which a network is trained on one task and re-purposed on another, is often used to produce neural network classifiers when data is scarce or full-scale training is too costly. When the goal is to produce a model that…

Machine Learning · Computer Science 2020-02-24 Ali Shafahi , Parsa Saadatpanah , Chen Zhu , Amin Ghiasi , Christoph Studer , David Jacobs , Tom Goldstein

We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error. Inspired by the observation that linear…

Machine Learning · Computer Science 2023-11-13 Fnu Suya , Xiao Zhang , Yuan Tian , David Evans

Although deep-learning based video recognition models have achieved remarkable success, they are vulnerable to adversarial examples that are generated by adding human-imperceptible perturbations on clean video samples. As indicated in…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Zhipeng Wei , Jingjing Chen , Zuxuan Wu , Yu-Gang Jiang

Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model…

Machine Learning · Computer Science 2020-06-29 David Solans , Battista Biggio , Carlos Castillo

Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained with it or introduce backdoors. In this paper we present a…

Machine Learning · Computer Science 2021-06-08 Ilia Shumailov , Zakhar Shumaylov , Dmitry Kazhdan , Yiren Zhao , Nicolas Papernot , Murat A. Erdogdu , Ross Anderson

Despite their impressive performance, deep visual models are susceptible to transferable black-box adversarial attacks. Principally, these attacks craft perturbations in a target model-agnostic manner. However, surprisingly, we find that…

Machine Learning · Computer Science 2025-04-15 Mohammad A. A. K. Jalwana , Naveed Akhtar , Ajmal Mian , Nazanin Rahnavard , Mubarak Shah

In targeted poisoning attacks, an attacker manipulates an agent-environment interaction to force the agent into adopting a policy of interest, called target policy. Prior work has primarily focused on attacks that modify standard MDP…

Machine Learning · Computer Science 2023-02-28 Mohammad Mohammadi , Jonathan Nöther , Debmalya Mandal , Adish Singla , Goran Radanovic

Adversarial attacks insert small, imperceptible perturbations to input samples that cause large, undesired changes to the output of deep learning models. Despite extensive research on generating adversarial attacks and building defense…

Machine Learning · Computer Science 2023-06-27 Vyas Raina , Mark Gales

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial…

Computer Vision and Pattern Recognition · Computer Science 2017-02-14 Alexey Kurakin , Ian Goodfellow , Samy Bengio

Despite their tremendous success in a range of domains, deep learning systems are inherently susceptible to two types of manipulations: adversarial inputs -- maliciously crafted samples that deceive target deep neural network (DNN) models,…

Machine Learning · Computer Science 2020-11-24 Ren Pang , Hua Shen , Xinyang Zhang , Shouling Ji , Yevgeniy Vorobeychik , Xiapu Luo , Alex Liu , Ting Wang

Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing attack methods mainly focus on designing triggers or fusion…

Cryptography and Security · Computer Science 2023-07-17 Zihao Zhu , Mingda Zhang , Shaokui Wei , Li Shen , Yanbo Fan , Baoyuan Wu

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

Machine Learning · Computer Science 2020-06-08 Bai Li , Shiqi Wang , Suman Jana , Lawrence Carin

This paper will describe and analyze a new phenomenon that was not known before, which we call "Early Transferability". Its essence is that the adversarial perturbations transfer among different networks even at extremely early stages in…

Machine Learning · Computer Science 2022-06-10 Oriel BenShmuel

The rapid advancement of artificial intelligence within the realm of cybersecurity raises significant security concerns. The vulnerability of deep learning models in adversarial attacks is one of the major issues. In adversarial machine…

Cryptography and Security · Computer Science 2024-04-18 Khushnaseeb Roshan , Aasim Zafar

Advances in machine learning have led to broad deployment of systems with impressive performance on important problems. Nonetheless, these systems can be induced to make errors on data that are surprisingly similar to examples the learned…

Machine Learning · Computer Science 2018-07-23 Justin Gilmer , Ryan P. Adams , Ian Goodfellow , David Andersen , George E. Dahl