Masakatsu Nishigaki’s research while affiliated with Shizuoka University and other places

This paper discusses the attack feasibility of Remote Adversarial Patch (RAP) targeting face detectors. The RAP that targets face detectors is similar to the RAP that targets general object detectors, but the former has multiple issues in the attack process the latter does not. (1) It is possible to detect objects of various scales. In particular, the area of small objects that are convolved during feature extraction by CNN is small,so the area that affects the inference results is also small. (2) It is a two-class classification, so there is a large gap in characteristics between the classes. This makes it difficult to attack the inference results by directing them to a different class. In this paper, we propose a new patch placement method and loss function for each problem. The patches targeting the proposed face detector showed superior detection obstruct effects compared to the patches targeting the general object detector.

Multibiometrics, which uses multiple biometric traits to improve recognition performance instead of using only one biometric trait to authenticate individuals, has been investigated. Previous studies have combined individually acquired biometric traits or have not fully considered the convenience of the system.Focusing on a single face image, we propose a novel multibiometric method that combines five biometric traits, i.e., face, iris, periocular, nose, eyebrow, that can be extracted from a single face image. The proposed method does not sacrifice the convenience of biometrics since only a single face image is used as input.Through a variety of experiments using the CASIA Iris Distance database, we demonstrate the effectiveness of the proposed multibiometrics method.

Demographic bias is one of the major challenges for face recognition systems. The majority of existing studies on demographic biases are heavily dependent on specific demographic groups or demographic classifier, making it difficult to address performance for unrecognised groups. This paper introduces ``LabellessFace'', a novel framework that improves demographic bias in face recognition without requiring demographic group labeling typically required for fairness considerations. We propose a novel fairness enhancement metric called the class favoritism level, which assesses the extent of favoritism towards specific classes across the dataset. Leveraging this metric, we introduce the fair class margin penalty, an extension of existing margin-based metric learning. This method dynamically adjusts learning parameters based on class favoritism levels, promoting fairness across all attributes. By treating each class as an individual in facial recognition systems, we facilitate learning that minimizes biases in authentication accuracy among individuals. Comprehensive experiments have demonstrated that our proposed method is effective for enhancing fairness while maintaining authentication accuracy.

To improve the rate of taking security action, it is important to promote personalized approaches for each user. Related works indicate phrases and UIs of dialog messages and incentives that influence a user’s action. In our previous work, we focused on smartphone users updating software, and proposed appropriate phrases of dialog messages according to the user’s understanding of the updating procedure, as well as the type of software. We also analyzed appropriate incentives. However, in the terms of level of literacy, the effectiveness of the UI of dialog messages and the volume of incentives remain unclear. In this paper, we conducted a user survey to analyze appropriate UIs according to the user’s understanding of the updating procedure and the appropriate volume of incentives. As a result, we confirmed different UIs are effective according to the user’s understanding of the updating procedure. In addition, we found an appropriate volume of points, mobile data, and coupons in order to promote the updating of software.

Social engineering involves manipulating a target to make it act to achieve the attacker's objectives. Currently, direct and short-term attacks are common in the mainstream. However, with the development of science and technology, there has been a shift toward extended and long-term attacks using VR and other technologies. We define advanced persistent social engineering (APSE) as social engineering in which a sophisticated intrusion is continuously made in the psychological aspect of the target so that the target voluntarily behaves as intended by the attacker. Countermeasures against APSE attacks have not been studied yet. We propose a method to detect APSE attacks by checking for inconsistencies in personality because the principles of human behavior (personality) do not change easily but change when others intrude.

Some users (“Help recipients”) delegate necessary security actions to their family, friends, or others close to them. It is important to be able to take appropriate defensive actions against security threats by themselves when help is not available from neighbors (“Helpers”). In this paper, we interviewed 9 users who used to be Help recipients, but who have now started to take security actions by themselves. We investigated the reason why Help recipients delegated their security actions to Helpers and the human factors that have an impact when one takes security actions by oneself. As a result, Help recipients take their own security actions when they try new hobbies or feel a sense of ownership. Based on these findings, we classify Help recipients into four groups and propose an optimized system that shows security action lists according to user situation. These findings are useful when providing appropriate intervention for Help recipients.