arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.08285cs.CVcs.AIcs.SYeess.SY
收藏

图像识别中神经网络鲁棒性评估综述

A Survey of Neural Network Robustness Assessment in Image Recognition

Beihang University(北京航空航天大学)

Jie Wang, Jun Ai, Minyan Lu, Haoran Su, Dan Yu, Yutao Zhang, Junda Zhu, Jingyu Liu

AI总结:

该综述针对图像识别领域的神经网络鲁棒性评估,围绕对抗鲁棒性与损坏鲁棒性,从概念、指标、评估方法三方面梳理现有研究,分析方法优劣并提出未来研究方向。

摘要:

近年来,神经网络的鲁棒性评估受到了广泛关注。在复杂且不确定的环境中,鲁棒性对于确保人工智能(AI)系统的可靠运行起着至关重要的作用。随着针对图像分类模型的对抗攻击被发现,深度学习的鲁棒性问题显得尤为突出。研究人员已致力于评估图像识别任务在各类扰动条件下的鲁棒性。鲁棒性评估主要包含两类技术:针对蓄意对抗攻击的鲁棒性验证/认证,以及针对随机数据损坏的鲁棒性测试。本综述详细研究了神经网络评估中的对抗鲁棒性(AR)与损坏鲁棒性(CR)。通过分析现有研究论文与标准,本文对图像识别领域的鲁棒性评估进行了全面概述,从概念、指标、评估方法三个核心方面展开分析。文中调研了用于衡量图像扰动程度的扰动指标与范围表示方法,以及专门针对分类模型鲁棒性条件的鲁棒性指标,同时讨论了现有方法的优势与局限性,并给出了未来研究的若干潜在方向。

英文摘要:

In recent years, there has been significant attention given to the robustness assessment of neural networks. Robustness plays a critical role in ensuring reliable operation of artificial intelligence (AI) systems in complex and uncertain environments. Deep learning's robustness problem is particularly significant, highlighted by the discovery of adversarial attacks on image classification models. Researchers have dedicated efforts to evaluate robustness in diverse perturbation conditions for image recognition tasks. Robustness assessment encompasses two main techniques: robustness verification/ certification for deliberate adversarial attacks and robustness testing for random data corruptions. In this survey, we present a detailed examination of both adversarial robustness (AR) and corruption robustness (CR) in neural network assessment. Analyzing current research papers and standards, we provide an extensive overview of robustness assessment in image recognition. Three essential aspects are analyzed: concepts, metrics, and assessment methods. We investigate the perturbation metrics and range representations used to measure the degree of perturbations on images, as well as the robustness metrics specifically for the robustness conditions of classification models. The strengths and limitations of the existing methods are also discussed, and some potential directions for future research are provided.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑