Yutaka Oiwa

Yusuke Kawamoto, Kazumasa Miyake, Koichi Konishi et al.

In this article, we propose the Artificial Intelligence Security Taxonomy to systematize the knowledge of threats, vulnerabilities, and security controls of machine-learning-based (ML-based) systems. We first classify the damage caused by attacks against ML-based systems, define ML-specific security, and discuss its characteristics. Next, we enumerate all relevant assets and stakeholders and provide a general taxonomy for ML-specific threats. Then, we collect a wide range of security controls against ML-specific threats through an extensive review of recent literature. Finally, we classify the vulnerabilities and controls of an ML-based system in terms of each vulnerable asset in the system's entire lifecycle.

Tinghui Ouyang, Vicent Sant Marco, Yoshinao Isobe et al.

As the major factors affecting the safety of deep learning models, corner cases and related detection are crucial in AI quality assurance for constructing safety- and security-critical systems. The generic corner case researches involve two interesting topics. One is to enhance DL models robustness to corner case data via the adjustment on parameters/structure. The other is to generate new corner cases for model retraining and improvement. However, the complex architecture and the huge amount of parameters make the robust adjustment of DL models not easy, meanwhile it is not possible to generate all real-world corner cases for DL training. Therefore, this paper proposes to a simple and novel study aiming at corner case data detection via a specific metric. This metric is developed on surprise adequacy (SA) which has advantages on capture data behaviors. Furthermore, targeting at characteristics of corner case data, three modifications on distanced-based SA are developed for classification applications in this paper. Consequently, through the experiment analysis on MNIST data and industrial data, the feasibility and usefulness of the proposed method on corner case data detection are verified.

Ling Fang, Yoriyuki Yamagata, Yutaka Oiwa

If a Micro Processor Unit (MPU) receives an external electric signal as noise, the system function will freeze or malfunction easily. A new resilience strategy is implemented in order to reset the MPU automatically and stop the MPU from freezing or malfunctioning. The technique is useful for embedded systems which work in non-human environments. However, evaluating resilience strategies is difficult because their effectiveness depends on numerous, complex, interacting factors. In this paper, we use probabilistic model checking to evaluate the embedded systems installed with the above mentioned new resilience strategy. Qualitative evaluations are implemented with 6 PCTL formulas, and quantitative evaluations use two kinds of evaluation. One is system failure reduction, and the other is ADT (Average Down Time), the industry standard. Our work demonstrates the benefits brought by the resilience strategy. Experimental results indicate that our evaluation is cost-effective and reliable.