원문정보
초록
영어
AI technology is a central focus of the 4th Industrial Revolution. However, compared to some existing nonartificial intelligence technologies, new AI adversarial attacks have become possible in learning data management, input data management, and other areas. These attacks, which exploit weaknesses in AI encryption technology, are not only emerging as social issues but are also expected to have a significant negative impact on existing IT and convergence industries. This paper examines various cases of AI adversarial attacks developed recently, categorizes them into five groups, and provides a foundational document for developing security guidelines to verify their safety. The findings of this study confirm AI adversarial attacks that can be applied to various types of cryptographic modules (such as hardware cryptographic modules, software cryptographic modules, firmware cryptographic modules, hybrid software cryptographic modules, hybrid firmware cryptographic modules, etc.) incorporating AI technology. The aim is to offer a foundational document for the development of standardized protocols, believed to play a crucial role in rejuvenating the information security industry in the future.
목차
1. Introduction
2. Classification of adversarial attacks
3. Analysis of adversarial cases
3.1 Adversarial cases for image input or machine learning image dataset by adding physical image foreign substances
3.2 Adversarial cases for extract machine learning image dataset
3.3 Adversarial cases for voice input or machine learning voice dataset by adding physical voice foreign substances
3.4 Adversarial cases for extraction of some input actions
3.5 Adversarial cases for information leakage attack by side channel
3.6 Analysis results of adversarial attacks
4. Conclusion
Acknowledgement
References