English
Related papers

Related papers: Local Convolutions Cause an Implicit Bias towards …

200 papers

It is common practice to apply padding prior to convolution operations to preserve the resolution of feature-maps in Convolutional Neural Networks (CNN). While many alternatives exist, this is often achieved by adding a border of zeros…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Paul Gavrikov , Janis Keuper

We study the robustness of machine learning approaches to adversarial perturbations, with a focus on supervised learning scenarios. We find that typical phase classifiers based on deep neural networks are extremely vulnerable to adversarial…

Disordered Systems and Neural Networks · Physics 2024-01-26 Si Jiang , Sirui Lu , Dong-Ling Deng

Currently, a plethora of saliency models based on deep neural networks have led great breakthroughs in many complex high-level vision tasks (e.g. scene description, object detection). The robustness of these models, however, has not yet…

Computer Vision and Pattern Recognition · Computer Science 2019-04-03 Zhaohui Che , Ali Borji , Guangtao Zhai , Suiyi Ling , Guodong Guo , Patrick Le Callet

Deep learning systems have become ubiquitous in many aspects of our lives. Unfortunately, it has been shown that such systems are vulnerable to adversarial attacks, making them prone to potential unlawful uses. Designing deep neural…

Machine Learning · Computer Science 2018-06-04 Jan Svoboda , Jonathan Masci , Federico Monti , Michael M. Bronstein , Leonidas Guibas

Machine learning is vulnerable to adversarial examples-inputs designed to cause models to perform poorly. However, it is unclear if adversarial examples represent realistic inputs in the modeled domains. Diverse domains such as networks and…

Cryptography and Security · Computer Science 2021-11-09 Ryan Sheatsley , Blaine Hoak , Eric Pauley , Yohan Beugin , Michael J. Weisman , Patrick McDaniel

Federated learning learns a neural network model by aggregating the knowledge from a group of distributed clients under the privacy-preserving constraint. In this work, we show that this paradigm might inherit the adversarial vulnerability…

Machine Learning · Computer Science 2022-09-20 Yao Zhou , Jun Wu , Haixun Wang , Jingrui He

Deep learning has been a popular topic and has achieved success in many areas. It has drawn the attention of researchers and machine learning practitioners alike, with developed models deployed to a variety of settings. Along with its…

Machine Learning · Computer Science 2022-11-08 Daniel Steinberg , Paul Munro

Neural networks are known to be a class of highly expressive functions able to fit even random input-output mappings with $100\%$ accuracy. In this work, we present properties of neural networks that complement this aspect of expressivity.…

Convolutional neural networks are among the most successful architectures in deep learning with this success at least partially attributable to the efficacy of spatial invariance as an inductive bias. Locally connected layers, which differ…

Computer Vision and Pattern Recognition · Computer Science 2020-08-18 Gamaleldin F. Elsayed , Prajit Ramachandran , Jonathon Shlens , Simon Kornblith

Adversarial training is by far the most successful strategy for improving robustness of neural networks to adversarial attacks. Despite its success as a defense mechanism, adversarial training fails to generalize well to unperturbed test…

Machine Learning · Computer Science 2019-10-18 Yogesh Balaji , Tom Goldstein , Judy Hoffman

We study the error of linear regression in the face of adversarial attacks. In this framework, an adversary changes the input to the regression model in order to maximize the prediction error. We provide bounds on the prediction error in…

Machine Learning · Statistics 2023-03-29 Antônio H. Ribeiro , Thomas B. Schön

Despite the remarkable performance of deep neural networks on various computer vision tasks, they are known to be susceptible to adversarial perturbations, which makes it challenging to deploy them in real-world safety-critical…

Machine Learning · Computer Science 2020-07-03 Divyam Madaan , Jinwoo Shin , Sung Ju Hwang

It is widely acknowledged that trained convolutional neural networks (CNNs) have different levels of sensitivity to signals of different frequency. In particular, a number of empirical studies have documented CNNs sensitivity to…

Machine Learning · Computer Science 2023-09-27 Charles Godfrey , Elise Bishoff , Myles Mckay , Davis Brown , Grayson Jorgenson , Henry Kvinge , Eleanor Byler

Understanding the effect of depth in deep learning is a critical problem. In this work, we utilize the Fourier analysis to empirically provide a promising mechanism to understand why feedforward deeper learning is faster. To this end, we…

Machine Learning · Computer Science 2020-12-22 Zhi-Qin John Xu , Hanxu Zhou

While modern deep networks have demonstrated remarkable versatility, their training dynamics remain poorly understood--often driven more by empirical tweaks than architectural insight. This paper investigates how internal structural choices…

Machine Learning · Computer Science 2025-08-26 Saleh Nikooroo , Thomas Engel

In this paper, we investigate the use of pretraining with adversarial networks, with the objective of discovering the relationship between network depth and robustness. For this purpose, we selectively retrain different portions of VGG and…

Machine Learning · Computer Science 2021-11-01 Shoaib Ahmed Siddiqui , Thomas Breuel

Many learning problems involve symmetries, and while invariance can be built into neural architectures, it can also emerge implicitly when training on group-structured data. We study this phenomenon in classical Hopfield networks and show…

Machine Learning · Computer Science 2026-01-21 Michael Murray , Tenzin Chan , Kedar Karhadker , Christopher J. Hillar

Despite their unmatched performance, deep neural networks remain susceptible to targeted attacks by nearly imperceptible levels of adversarial noise. While the underlying cause of this sensitivity is not well understood, theoretical…

Machine Learning · Computer Science 2020-12-01 George Cazenavette , Calvin Murdock , Simon Lucey

Understanding the mechanism of how convolutional neural networks learn features from image data is a fundamental problem in machine learning and computer vision. In this work, we identify such a mechanism. We posit the Convolutional Neural…

Machine Learning · Statistics 2023-09-04 Daniel Beaglehole , Adityanarayanan Radhakrishnan , Parthe Pandit , Mikhail Belkin

The reliability of a learning model is key to the successful deployment of machine learning in various industries. Creating a robust model, particularly one unaffected by adversarial attacks, requires a comprehensive understanding of the…

Machine Learning · Computer Science 2022-08-16 Ramin Barati , Reza Safabakhsh , Mohammad Rahmati