arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.07045cs.LGstat.ML
收藏

语义对抗深度学习

Semantic Adversarial Deep Learning

University of California at Berkeley(加州大学伯克利分校);University of Wisconsin(威斯康星大学)

Tommaso Dreossi, Somesh Jha, Sanjit A. Seshia

摘要:

在大量数据的推动下,机器学习(ML)算法(尤其是深度神经网络)生成的模型正被用于值得关注的各种领域,包括汽车系统、金融、医疗保健、自然语言处理和恶意软件检测。特别值得关注的是机器学习算法在网络物理系统(CPS)中的使用,例如自动驾驶汽车和航空,在这些系统中,对手可能会造成严重后果。然而,现有的生成对抗性示例和设计鲁棒ML算法的方法大多忽略了包含ML组件的整个系统的语义和上下文。例如,在使用深度学习进行感知的自动驾驶汽车中,并非神经网络的每个对抗性示例都可能导致有害后果。此外,人们可能希望优先搜索对抗性示例,以显著修改整个系统的所需语义。沿着同样的路线,现有的算法,用于构建强大的ML算法忽略了整个系统的规范。在本文中,我们认为,整个系统的语义和规范在这条线的研究中发挥了至关重要的作用。我们目前的初步研究结果支持这一说法。

英文摘要:

Fueled by massive amounts of data, models produced by machine-learning (ML) algorithms, especially deep neural networks, are being used in diverse domains where trustworthiness is a concern, including automotive systems, finance, health care, natural language processing, and malware detection. Of particular concern is the use of ML algorithms in cyber-physical systems (CPS), such as self-driving cars and aviation, where an adversary can cause serious consequences. However, existing approaches to generating adversarial examples and devising robust ML algorithms mostly ignore the semantics and context of the overall system containing the ML component. For example, in an autonomous vehicle using deep learning for perception, not every adversarial example for the neural network might lead to a harmful consequence. Moreover, one may want to prioritize the search for adversarial examples towards those that significantly modify the desired semantics of the overall system. Along the same lines, existing algorithms for constructing robust ML algorithms ignore the specification of the overall system. In this paper, we argue that the semantics and specification of the overall system has a crucial role to play in this line of research. We present preliminary research results that support this claim.

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。

↑