arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.04790cs.LGstat.ML
收藏

对抗性实例:机遇与挑战

Adversarial Examples: Opportunities and Challenges

Hunan University(湖南大学);Peng Cheng Laboratory(鹏城实验室)

Jiliang Zhang, Chen Li

摘要:

深度神经网络(DNN)在图像识别、语音处理、自动驾驶汽车和医疗诊断方面表现出了超越人类的巨大优势。然而,最近的研究表明,DNN容易受到攻击者设计的对抗性示例(AE)的影响,这些示例是为了欺骗深度学习模型。与真实例子不同,AE可能会误导模型预测错误的输出,而人眼几乎无法区分,因此威胁到安全关键的深度学习应用。近年来,AE的产生和防御已成为人工智能(AI)安全领域的研究热点。本文就不良事件的最新研究进展作一综述。本文首先介绍了声发射的概念、产生原因、特点和评价指标,然后对现有的声发射生成方法进行了综述,并讨论了它们的优缺点。之后,我们将回顾现有的防御措施,并讨论其局限性。最后展望了未来AE研究的机遇和挑战。

英文摘要:

Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs), which are designed by attackers to fool deep learning models. Different from real examples, AEs can mislead the model to predict incorrect outputs while hardly be distinguished by human eyes, therefore threaten security-critical deep-learning applications. In recent years, the generation and defense of AEs have become a research hotspot in the field of artificial intelligence (AI) security. This article reviews the latest research progress of AEs. First, we introduce the concept, cause, characteristics and evaluation metrics of AEs, then give a survey on the state-of-the-art AE generation methods with the discussion of advantages and disadvantages. After that, we review the existing defenses and discuss their limitations. Finally, future research opportunities and challenges on AEs are prospected.

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。

↑