中文
相关论文

相关论文: Experimental demonstration of adversarial examples…

200 篇论文

In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we argued that adversarial examples in machine learning might be due to an inherent computational hardness of the problem. More precisely, we constructed a binary…

机器学习 · 计算机科学 2018-11-16 Sébastien Bubeck , Yin Tat Lee , Eric Price , Ilya Razenshteyn

The detection of phase transitions is a fundamental challenge in condensed matter physics, traditionally addressed through analytical methods and direct numerical simulations. In recent years, machine learning techniques have emerged as…

无序系统与神经网络 · 物理学 2025-01-14 Djenabou Bayo , Burak Çivitcioğlu , Joseph J Webb , Andreas Honecker , Rudolf A. Römer

Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial…

机器学习 · 计算机科学 2025-02-18 Jon Vadillo , Roberto Santana , Jose A. Lozano

In recent years, deep learning has shown performance breakthroughs in many applications, such as image detection, image segmentation, pose estimation, and speech recognition. However, this comes with a major concern: deep networks have been…

机器学习 · 计算机科学 2019-01-11 Felix Kreuk , Assi Barak , Shir Aviv-Reuven , Moran Baruch , Benny Pinkas , Joseph Keshet

The extreme fragility of deep neural networks, when presented with tiny perturbations in their inputs, was independently discovered by several research groups in 2013. However, despite enormous effort, these adversarial examples remained a…

机器学习 · 计算机科学 2022-06-02 Adi Shamir , Odelia Melamed , Oriel BenShmuel

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…

机器学习 · 计算机科学 2019-10-18 Yogesh Balaji , Tom Goldstein , Judy Hoffman

The ability to deploy neural networks in real-world, safety-critical systems is severely limited by the presence of adversarial examples: slightly perturbed inputs that are misclassified by the network. In recent years, several techniques…

机器学习 · 计算机科学 2018-02-21 Nicholas Carlini , Guy Katz , Clark Barrett , David L. Dill

With recent developments of convolutional neural networks, deep learning for 3D point clouds has shown significant progress in various 3D scene understanding tasks, e.g., object recognition, semantic segmentation. In a safety-critical…

计算机视觉与模式识别 · 计算机科学 2021-09-20 Jaeyeon Kim , Binh-Son Hua , Duc Thanh Nguyen , Sai-Kit Yeung

Artificial neural networks and machine learning have now reached a new era after several decades of improvement where applications are to explode in many fields of science, industry, and technology. Here, we use artificial neural networks…

无序系统与神经网络 · 物理学 2017-11-23 Dong-Ling Deng , Xiaopeng Li , S. Das Sarma

Machine-learning driven models have proven to be powerful tools for the identification of phases of matter. In particular, unsupervised methods hold the promise to help discover new phases of matter without the need for any prior…

We demonstrate the identification and classification of topological phase transitions from experimental data using Diffusion Maps: a nonlocal unsupervised machine learning method. We analyze experimental data from an optical system…

光学 · 物理学 2021-04-09 Eran Lustig , Or Yair , Ronen Talmon , Mordechai Segev

It has been shown that most machine learning algorithms are susceptible to adversarial perturbations. Slightly perturbing an image in a carefully chosen direction in the image space may cause a trained neural network model to misclassify…

计算机视觉与模式识别 · 计算机科学 2017-07-13 Jiajun Lu , Hussein Sibai , Evan Fabry , David Forsyth

The classification of phase transitions is a central and challenging task in condensed matter physics. Typically, it relies on the identification of order parameters and the analysis of singularities in the free energy and its derivatives.…

Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…

机器学习 · 计算机科学 2020-04-28 Jan Philip Göpfert , André Artelt , Heiko Wersing , Barbara Hammer

Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding…

机器学习 · 计算机科学 2021-12-03 Siyu Wang , Yuanjiang Cao , Xiaocong Chen , Lina Yao , Xianzhi Wang , Quan Z. Sheng

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…

机器学习 · 计算机科学 2022-08-16 Ramin Barati , Reza Safabakhsh , Mohammad Rahmati

There has been growing excitement over the possibility of employing artificial neural networks (ANNs) to gain new theoretical insight into the physics of quantum many-body problems. ``Interpretability'' remains a concern: can we understand…

无序系统与神经网络 · 物理学 2020-12-08 Yi Zhang , Paul Ginsparg , Eun-Ah Kim

Adversarial defenses protect machine learning models from adversarial attacks, but are often tailored to one type of model or attack. The lack of information on unknown potential attacks makes detecting adversarial examples challenging.…

机器学习 · 计算机科学 2023-09-15 Xinglong Chang , Katharina Dost , Kaiqi Zhao , Ambra Demontis , Fabio Roli , Gill Dobbie , Jörg Wicker

Many machine learning models are vulnerable to adversarial examples: inputs that are specially crafted to cause a machine learning model to produce an incorrect output. Adversarial examples that affect one model often affect another model,…

密码学与安全 · 计算机科学 2016-05-25 Nicolas Papernot , Patrick McDaniel , Ian Goodfellow

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…

机器学习 · 计算机科学 2017-02-09 Sandy Huang , Nicolas Papernot , Ian Goodfellow , Yan Duan , Pieter Abbeel