Visible to the public Biblio

Filters: Author is Otsuka, A.  [Clear All Filters]
Conference Paper
Imai, H., Hanaoka, G., Shikata, J., Otsuka, A., Nascimento, A. C..  2002.  Cryptography with information theoretic security. Proceedings of the IEEE Information Theory Workshop. :73–.
Summary form only given. We discuss information-theoretic methods to prove the security of cryptosystems. We study what is called, unconditionally secure (or information-theoretically secure) cryptographic schemes in search for a system that can provide long-term security and that does not impose limits on the adversary's computational power.
Kadoguchi, M., Kobayashi, H., Hayashi, S., Otsuka, A., Hashimoto, M..  2020.  Deep Self-Supervised Clustering of the Dark Web for Cyber Threat Intelligence. 2020 IEEE International Conference on Intelligence and Security Informatics (ISI). :1—6.

In recent years, cyberattack techniques have become more and more sophisticated each day. Even if defense measures are taken against cyberattacks, it is difficult to prevent them completely. It can also be said that people can only fight defensively against cyber criminals. To address this situation, it is necessary to predict cyberattacks and take appropriate measures in advance, and the use of intelligence is important to make this possible. In general, many malicious hackers share information and tools that can be used for attacks on the dark web or in the specific communities. Therefore, we assume that a lot of intelligence, including this illegal content exists in cyber space. By using the threat intelligence, detecting attacks in advance and developing active defense is expected these days. However, such intelligence is currently extracted manually. In order to do this more efficiently, we apply machine learning to various forum posts that exist on the dark web, with the aim of extracting forum posts containing threat information. By doing this, we expect that detecting threat information in cyber space in a timely manner will be possible so that the optimal preventive measures will be taken in advance.

Kobayashi, H., Kadoguchi, M., Hayashi, S., Otsuka, A., Hashimoto, M..  2020.  An Expert System for Classifying Harmful Content on the Dark Web. 2020 IEEE International Conference on Intelligence and Security Informatics (ISI). :1—6.

In this research, we examine and develop an expert system with a mechanism to automate crime category classification and threat level assessment, using the information collected by crawling the dark web. We have constructed a bag of words from 250 posts on the dark web and developed an expert system which takes the frequency of terms as an input and classifies sample posts into 6 criminal category dealing with drugs, stolen credit card, passwords, counterfeit products, child porn and others, and 3 threat levels (high, middle, low). Contrary to prior expectations, our simple and explainable expert system can perform competitively with other existing systems. For short, our experimental result with 1500 posts on the dark web shows 76.4% of recall rate for 6 criminal category classification and 83% of recall rate for 3 threat level discrimination for 100 random-sampled posts.