中文
相关论文

相关论文: Robust Assessment of Real-World Adversarial Exampl…

200 篇论文

With an ever-increasing reliance on machine learning (ML) models in the real world, adversarial examples threaten the safety of AI-based systems such as autonomous vehicles. In the image domain, they represent maliciously perturbed data…

The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an…

机器学习 · 计算机科学 2019-11-28 Chao Tang , Yifei Fan , Anthony Yezzi

Robot evaluations in language-guided, real world settings are time-consuming and often sample only a small space of potential instructions across complex scenes. In this work, we introduce contrast sets for robotics as an approach to make…

机器人学 · 计算机科学 2024-10-28 Abrar Anwar , Rohan Gupta , Jesse Thomason

Despite the significant advances in deep learning over the past decade, a major challenge that limits the wide-spread adoption of deep learning has been their fragility to adversarial attacks. This sensitivity to making erroneous…

The phenomenon of adversarial examples in deep learning models has caused substantial concern over their reliability. While many deep neural networks have shown impressive performance in terms of predictive accuracy, it has been shown that…

机器学习 · 计算机科学 2021-06-28 Sadia Chowdhury , Ruth Urner

Autonomous vehicles must be comprehensively evaluated before deployed in cities and highways. However, most existing evaluation approaches for autonomous vehicles are static and lack adaptability, so they are usually inefficient in…

机器人学 · 计算机科学 2020-11-25 Baiming Chen , Xiang Chen , Wu Qiong , Liang Li

Trajectory prediction is a key element of autonomous vehicle systems, enabling them to anticipate and react to the movements of other road users. Evaluating the robustness of prediction models against adversarial attacks is essential to…

机器学习 · 计算机科学 2025-05-12 Julian F. Schumann , Jeroen Hagenus , Frederik Baymler Mathiesen , Arkady Zgonnikov

A new understanding of adversarial examples and adversarial robustness is proposed by decoupling the data generator and the label generator (which we call the teacher). In our framework, adversarial robustness is a conditional concept---the…

机器学习 · 计算机科学 2020-12-15 Chao Ma , Lexing Ying

Adversarial examples have appeared as a ubiquitous property of machine learning models where bounded adversarial perturbation could mislead the models to make arbitrarily incorrect predictions. Such examples provide a way to assess the…

机器学习 · 计算机科学 2021-03-02 Zhuolin Yang , Zhaoxi Chen , Tiffany Cai , Xinyun Chen , Bo Li , Yuandong Tian

Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…

机器学习 · 计算机科学 2023-06-14 Omar Montasser

The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing that one can extract…

机器学习 · 计算机科学 2024-05-07 Ang Li , Yifei Wang , Yiwen Guo , Yisen Wang

This paper studies the problem of detecting adversarial perturbations in a sequence of observations. Given a data sample $X_1, \ldots, X_n$ drawn from a standard normal distribution, an adversary, after observing the sample, can perturb…

概率论 · 数学 2024-10-28 Gleb Smirnov

In this paper, we propose a natural and robust physical adversarial example attack method targeting object detectors under real-world conditions. The generated adversarial examples are robust to various physical constraints and visually…

计算机视觉与模式识别 · 计算机科学 2021-03-18 Mingfu Xue , Chengxiang Yuan , Can He , Jian Wang , Weiqiang Liu

Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning…

计算机视觉与模式识别 · 计算机科学 2017-02-14 Alexey Kurakin , Ian Goodfellow , Samy Bengio

This paper investigates recently proposed approaches for defending against adversarial examples and evaluating adversarial robustness. We motivate 'adversarial risk' as an objective for achieving models robust to worst-case inputs. We then…

机器学习 · 计算机科学 2018-06-13 Jonathan Uesato , Brendan O'Donoghue , Aaron van den Oord , Pushmeet Kohli

Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence…

机器学习 · 计算机科学 2020-11-04 Tao Bai , Jinqi Luo , Jun Zhao

Although current deep learning techniques have yielded superior performance on various computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial training and its variants have been shown to be the most…

计算机视觉与模式识别 · 计算机科学 2022-11-02 Junhao Dong , Seyed-Mohsen Moosavi-Dezfooli , Jianhuang Lai , Xiaohua Xie

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

计算机视觉与模式识别 · 计算机科学 2023-06-27 Levente Halmosi , Mark Jelasity

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

Current studies on adversarial robustness mainly focus on aggregating local robustness results from a set of data samples to evaluate and rank different models. However, the local statistics may not well represent the true global robustness…

机器学习 · 计算机科学 2024-10-29 Zaitang Li , Pin-Yu Chen , Tsung-Yi Ho