Takayuki Sasaki

Teppei Kurita, Yuhi Kondo, Legong Sun et al.

In this study, we propose a high-performance disparity (depth) estimation method using dual-pixel (DP) images with few parameters. Conventional end-to-end deep-learning methods have many parameters but do not fully exploit disparity constraints, which limits their performance. Therefore, we propose a lightweight disparity estimation method based on a completion-based network that explicitly constrains disparity and learns the physical and systemic disparity properties of DP. By modeling the DP-specific disparity error parametrically and using it for sampling during training, the network acquires the unique properties of DP and enhances robustness. This learning also allows us to use a common RGB-D dataset for training without a DP dataset, which is labor-intensive to acquire. Furthermore, we propose a non-learning-based refinement framework that efficiently handles inherent disparity expansion errors by appropriately refining the confidence map of the network output. As a result, the proposed method achieved state-of-the-art results while reducing the overall system size to 1/5 of that of the conventional method, even without using the DP dataset for training, thereby demonstrating its effectiveness. The code and dataset are available on our project site.

Takayuki Sasaki, Shuichi Karino, Mikiya Tani et al.

Systems using 5G are expected to be used in various cases of Society 5.0 and Industrie 4.0 such as smart cities, smart factories, and also critical infrastructures. These systems are essential for our life, thus cyberattacks against the system must be prevented. In this paper, we tackle two problems posed by 5G features: system construction using multi-vendor devices and softwarized functions. Specifically, there are supply-chain risks that malicious devices are used in the construction phase. Moreover, the softwarized network functions are easy to be attacked compared to hardware. To cope with these problems, we propose a concept of architecture comprising a blockchain to record security events including supply-chain information and a tamper detection engine to ensure the integrity of software components in 5G system. We implement the initial prototype of the architecture and show its feasibility.

Takayuki Sasaki, Yusuke Shimada

To keep a system secure, all devices in the system need to be benign. To avoid malicious and/or compromised devices, network access control such as authentication using a credential and remote attestation based on trusted hardware has been used. These techniques ensure the authenticity and integrity of the devices, but do not mitigate risks of a backdoor embedded in the devices by the developer. To tackle this problem, we propose a novel architecture that integrates remote attestation and backdoor inspection. Specifically, the backdoor inspection result is stored in a server and the verifier retrieves and checks the backdoor inspection result when the remote attestation is performed. Moreover, we discuss issues to deploy the proposed architecture to the real world.