English
Related papers

Related papers: On the transferability of adversarial examples bet…

200 papers

In this work, we evaluate adversarial robustness in the context of transfer learning from a source trained on CIFAR 100 to a target network trained on CIFAR 10. Specifically, we study the effects of using robust optimisation in the source…

Machine Learning · Statistics 2019-06-11 Todor Davchev , Timos Korres , Stathi Fotiadis , Nick Antonopoulos , Subramanian Ramamoorthy

Evaluating on adversarial examples has become a standard procedure to measure robustness of deep learning models. Due to the difficulty of creating white-box adversarial examples for discrete text input, most analyses of the robustness of…

Computation and Language · Computer Science 2018-06-26 Javid Ebrahimi , Daniel Lowd , Dejing Dou

The vulnerability of deep neural networks (DNNs) to adversarial examples has drawn great attention from the community. In this paper, we study the transferability of such examples, which lays the foundation of many black-box attacks on…

Machine Learning · Computer Science 2020-12-08 Yiwen Guo , Qizhang Li , Hao Chen

Despite their impressive performance, deep neural networks exhibit striking failures on out-of-distribution inputs. One core idea of adversarial example research is to reveal neural network errors under such distribution shifts. We…

Machine Learning · Computer Science 2020-07-14 Jörn-Henrik Jacobsen , Jens Behrmann , Richard Zemel , Matthias Bethge

Neural networks are susceptible to adversarial perturbations that are transferable across different models. In this paper, we introduce a novel model alignment technique aimed at improving a given source model's ability in generating…

Machine Learning · Computer Science 2024-07-18 Avery Ma , Amir-massoud Farahmand , Yangchen Pan , Philip Torr , Jindong Gu

Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these examples is their transferability, allowing them to deceive…

Cryptography and Security · Computer Science 2025-04-22 Yi Yu , Song Xia , Xun Lin , Chenqi Kong , Wenhan Yang , Shijian Lu , Yap-Peng Tan , Alex C. Kot

Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle perturbations applied to inputs that are often imperceptible to humans yet lead to incorrect model predictions. In black-box scenarios, however, existing…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Qing Wan , Shilong Deng , Xun Wang

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to…

Machine Learning · Computer Science 2018-02-14 Angus Galloway , Graham W. Taylor , Medhat Moussa

In recent years, defending adversarial perturbations to natural examples in order to build robust machine learning models trained by deep neural networks (DNNs) has become an emerging research field in the conjunction of deep learning and…

Computer Vision and Pattern Recognition · Computer Science 2018-05-10 Pei-Hsuan Lu , Pin-Yu Chen , Kang-Cheng Chen , Chia-Mu Yu

Flatness of the loss surface not only correlates positively with generalization, but is also related to adversarial robustness since perturbations of inputs relate non-linearly to perturbations of weights. In this paper, we empirically…

Machine Learning · Computer Science 2025-03-11 Nils Philipp Walter , Linara Adilova , Jilles Vreeken , Michael Kamp

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…

Computer Vision and Pattern Recognition · Computer Science 2020-09-04 Alex Serban , Erik Poll , Joost Visser

Shift invariance is a critical property of CNNs that improves performance on classification. However, we show that invariance to circular shifts can also lead to greater sensitivity to adversarial attacks. We first characterize the margin…

Machine Learning · Computer Science 2021-11-23 Songwei Ge , Vasu Singla , Ronen Basri , David Jacobs

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

Transfer learning is a widely-used paradigm in deep learning, where models pre-trained on standard datasets can be efficiently adapted to downstream tasks. Typically, better pre-trained models yield better transfer results, suggesting that…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Hadi Salman , Andrew Ilyas , Logan Engstrom , Ashish Kapoor , Aleksander Madry

Despite the considerable success of convolutional neural networks in a broad array of domains, recent research has shown these to be vulnerable to small adversarial perturbations, commonly known as adversarial examples. Moreover, such…

Machine Learning · Computer Science 2018-12-06 Yifan Chen , Yevgeniy Vorobeychik

Previous work has proposed many new loss functions and regularizers that improve test accuracy on image classification tasks. However, it is not clear whether these loss functions learn better representations for downstream tasks. This…

Computer Vision and Pattern Recognition · Computer Science 2021-11-05 Simon Kornblith , Ting Chen , Honglak Lee , Mohammad Norouzi

Adversarial training and its variants have become de facto standards for learning robust deep neural networks. In this paper, we explore the landscape around adversarial training in a bid to uncover its limits. We systematically study the…

Machine Learning · Statistics 2021-03-31 Sven Gowal , Chongli Qin , Jonathan Uesato , Timothy Mann , Pushmeet Kohli

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

Failure cases of black-box deep learning, e.g. adversarial examples, might have severe consequences in healthcare. Yet such failures are mostly studied in the context of real-world images with calibrated attacks. To demystify the…

Computer Vision and Pattern Recognition · Computer Science 2018-11-14 David Kügler , Alexander Distergoft , Arjan Kuijper , Anirban Mukhopadhyay

Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this…

Computer Vision and Pattern Recognition · Computer Science 2018-09-11 Zukang Liao