English
Related papers

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

200 papers

Adversarial examples are maliciously perturbed inputs designed to mislead machine learning (ML) models at test-time. They often transfer: the same adversarial example fools more than one model. In this work, we propose novel methods for…

Machine Learning · Statistics 2017-05-25 Florian Tramèr , Nicolas Papernot , Ian Goodfellow , Dan Boneh , Patrick McDaniel

Transferable adversarial attacks against Deep neural networks (DNNs) have received broad attention in recent years. An adversarial example can be crafted by a surrogate model and then attack the unknown target model successfully, which…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Yao Zhu , Yuefeng Chen , Xiaodan Li , Kejiang Chen , Yuan He , Xiang Tian , Bolun Zheng , Yaowu Chen , Qingming Huang

The transferability of adversarial examples allows for the attack on unknown deep neural networks (DNNs), posing a serious threat to many applications and attracting great attention. In this paper, we improve the transferability of…

Machine Learning · Computer Science 2025-10-16 Qizhang Li , Yiwen Guo , Xiaochen Yang , Wangmeng Zuo , Hao Chen

Making learners robust to adversarial perturbation at test time (i.e., evasion attacks) or training time (i.e., poisoning attacks) has emerged as a challenging task. It is known that for some natural settings, sublinear perturbations in the…

Machine Learning · Computer Science 2018-11-07 Saeed Mahloujifar , Mohammad Mahmoody

This paper examines the robustness of deployed few-shot meta-learning systems when they are fed an imperceptibly perturbed few-shot dataset. We attack amortized meta-learners, which allows us to craft colluding sets of inputs that are…

Machine Learning · Computer Science 2022-11-24 Elre T. Oldewage , John Bronskill , Richard E. Turner

It is well-known that deep learning models are vulnerable to small input perturbations. Such perturbed instances are called adversarial examples. Adversarial examples are commonly crafted to fool a model either at training time (poisoning)…

Machine Learning · Computer Science 2023-12-12 Ege Erdogan , Simon Geisler , Stephan Günnemann

In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in favor of the adversary. We consider poisoning attacks…

Machine Learning · Computer Science 2021-04-22 Fnu Suya , Saeed Mahloujifar , Anshuman Suri , David Evans , Yuan Tian

Adversarial patches in computer vision can be used, to fool deep neural networks and manipulate their decision-making process. One of the most prominent examples of adversarial patches are evasion attacks for object detectors. By covering…

Computer Vision and Pattern Recognition · Computer Science 2025-04-25 Jens Bayer , Stefan Becker , David Münch , Michael Arens

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Deep Learning models hold state-of-the-art performance in many fields, but their vulnerability to adversarial examples poses threat to their ubiquitous deployment in practical settings. Additionally, adversarial inputs generated on one…

Machine Learning · Computer Science 2021-03-31 Deepak Ravikumar , Sangamesh Kodge , Isha Garg , Kaushik Roy

Deep neural networks are vulnerable to adversarial examples (AEs), which have adversarial transferability: AEs generated for the source model can mislead another (target) model's predictions. However, the transferability has not been…

Machine Learning · Computer Science 2022-10-21 Futa Waseda , Sosuke Nishikawa , Trung-Nghia Le , Huy H. Nguyen , Isao Echizen

Two widely used techniques for training supervised machine learning models on small datasets are Active Learning and Transfer Learning. The former helps to optimally use a limited budget to label new data. The latter uses large pre-trained…

Machine Learning · Computer Science 2021-01-28 Nicolas M. Müller , Konstantin Böttinger

We analysis performance of semantic segmentation models wrt. adversarial attacks, and observe that the adversarial examples generated from a source model fail to attack the target models. i.e The conventional attack methods, such as PGD and…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Mengqi He , Jing Zhang , Zhaoyuan Yang , Mingyi He , Nick Barnes , Yuchao Dai

Transfer adversarial attacks raise critical security concerns in real-world, black-box scenarios. However, the actual progress of this field is difficult to assess due to two common limitations in existing evaluations. First, different…

Cryptography and Security · Computer Science 2023-10-31 Zhengyu Zhao , Hanwei Zhang , Renjue Li , Ronan Sicre , Laurent Amsaleg , Michael Backes

Deep neural networks (DNNs) can be easily fooled by adding human imperceptible perturbations to the images. These perturbed images are known as `adversarial examples' and pose a serious threat to security and safety critical systems. A…

Computer Vision and Pattern Recognition · Computer Science 2019-03-27 Muzammal Naseer , Salman H. Khan , Shafin Rahman , Fatih Porikli

Evasion attack in multi-label learning systems is an interesting, widely witnessed, yet rarely explored research topic. Characterizing the crucial factors determining the attackability of the multi-label adversarial threat is the key to…

Machine Learning · Computer Science 2020-12-22 Zhuo Yang , Yufei Han , Xiangliang Zhang

Recent studies have shown that Convolutional Neural Networks (CNN) are relatively easy to attack through the generation of so-called adversarial examples. Such vulnerability also affects CNN-based image forensic tools. Research in deep…

Cryptography and Security · Computer Science 2018-11-06 Mauro Barni , Kassem Kallas , Ehsan Nowroozi , Benedetta Tondi

Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…

Machine Learning · Computer Science 2025-03-11 Daryna Oliynyk , Rudolf Mayer , Andreas Rauber

Deep learning-based image denoising models demonstrate remarkable performance, but their lack of robustness analysis remains a significant concern. A major issue is that these models are susceptible to adversarial attacks, where small,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-29 Jie Ning , Jiebao Sun , Shengzhu Shi , Zhichang Guo , Yao Li , Hongwei Li , Boying Wu

Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…

Machine Learning · Computer Science 2021-10-13 Bingyin Zhao , Yingjie Lao