arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.16491cs.CV
收藏

主动方案:面向社会公益的对抗性攻击综述

Proactive Schemes: A Survey of Adversarial Attacks for Social Good

Michigan State University(密歇根州立大学);Meta AI

Vishal Asnani, Xi Yin, Xiaoming Liu

AI总结:

本综述探讨了利用对抗技术促进社会公益的主动方案,即通过向输入数据嵌入附加模板信号来增强深度学习模型性能,并分析了其方法、应用及未来发展方向。

摘要:

计算机视觉中的对抗性攻击通过向输入数据引入细微扰动来利用机器学习模型的漏洞,通常会导致错误的预测或分类。随着深度学习的出现,这些攻击的复杂性不断演变,在关键应用中带来了重大挑战,这可能对社会造成危害。然而,也存在一条丰富的转化视角研究路线,利用对抗技术促进社会公益。具体而言,我们探讨了主动方案的兴起——即使用称为模板的附加信号对输入数据进行加密,以增强深度学习模型性能的方法。通过将这些难以察觉的模板嵌入数字媒体,主动方案被应用于各种应用中,从简单的图像增强到复杂的深度学习框架以辅助提升性能,相比之下,被动方案不会改变其框架的输入数据分布。本综述深入探讨了这些主动方案背后的方法论、加密和学习过程,及其在现代计算机视觉和自然语言处理中的应用。此外,还讨论了主动方案面临的挑战、潜在漏洞和未来方向,最终强调了它们在促进深度学习技术负责任且安全地发展方面的潜力。

英文摘要:

Adversarial attacks in computer vision exploit the vulnerabilities of machine learning models by introducing subtle perturbations to input data, often leading to incorrect predictions or classifications. These attacks have evolved in sophistication with the advent of deep learning, presenting significant challenges in critical applications, which can be harmful for society. However, there is also a rich line of research from a transformative perspective that leverages adversarial techniques for social good. Specifically, we examine the rise of proactive schemes-methods that encrypt input data using additional signals termed templates, to enhance the performance of deep learning models. By embedding these imperceptible templates into digital media, proactive schemes are applied across various applications, from simple image enhancements to complicated deep learning frameworks to aid performance, as compared to the passive schemes, which don't change the input data distribution for their framework. The survey delves into the methodologies behind these proactive schemes, the encryption and learning processes, and their application to modern computer vision and natural language processing applications. Additionally, it discusses the challenges, potential vulnerabilities, and future directions for proactive schemes, ultimately highlighting their potential to foster the responsible and secure advancement of deep learning technologies.

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。

↑