The Experts below are selected from a list of 358164 Experts worldwide ranked by ideXlab platform

Shoichi Hirose - One of the best experts on this subject based on the ideXlab platform.

  • ICISC - Provably secure double-block-length hash functions in a Black-Box Model
    Lecture Notes in Computer Science, 2005
    Co-Authors: Shoichi Hirose
    Abstract:

    In CRYPTO’89, Merkle presented three double-block-length hash functions based on DES. They are optimally collision resistant in a Black-Box Model, that is, the time complexity of any collision-finding algorithm for them is Ω(2l/2) if DES is a random block cipher, where l is the output length. Their drawback is that their rates are low. In this article, new double-block-length hash functions with higher rates are presented which are also optimally collision resistant in the Black-Box Model. They are composed of block ciphers whose key length is twice larger than their block length.

  • provably secure double block length hash functions in a black box Model
    International Conference on Information Security and Cryptology, 2004
    Co-Authors: Shoichi Hirose
    Abstract:

    In CRYPTO’89, Merkle presented three double-block-length hash functions based on DES. They are optimally collision resistant in a Black-Box Model, that is, the time complexity of any collision-finding algorithm for them is Ω(2l/2) if DES is a random block cipher, where l is the output length. Their drawback is that their rates are low. In this article, new double-block-length hash functions with higher rates are presented which are also optimally collision resistant in the Black-Box Model. They are composed of block ciphers whose key length is twice larger than their block length.

Jungwoo Lee - One of the best experts on this subject based on the ideXlab platform.

  • REST: Performance Improvement of a Black Box Model via RL-Based Spatial Transformation
    Proceedings of the AAAI Conference on Artificial Intelligence, 2020
    Co-Authors: Jae Myung Kim, Hyungjin Kim, Chanwoo Park, Jungwoo Lee
    Abstract:

    In recent years, deep neural networks (DNN) have become a highly active area of research, and shown remarkable achievements on a variety of computer vision tasks. DNNs, however, are known to often make overconfident yet incorrect predictions on out-of-distribution samples, which can be a major obstacle to real-world deployments because the training dataset is always limited compared to diverse real-world samples. Thus, it is fundamental to provide guarantees of robustness to the distribution shift between training and test time when we construct DNN Models in practice. Moreover, in many cases, the deep learning Models are deployed as black boxes and the performance has been already optimized for a training dataset, thus changing the black box itself can lead to performance degradation. We here study the robustness to the geometric transformations in a specific condition where the Black-Box image classifier is given. We propose an additional learner, REinforcement Spatial Transform learner (REST), that transforms the warped input data into samples regarded as in-distribution by the Black-Box Models. Our work aims to improve the robustness by adding a REST module in front of any black boxes and training only the REST module without retraining the original black box Model in an end-to-end manner, i.e. we try to convert the real-world data into training distribution which the performance of the Black-Box Model is best suited for. We use a confidence score that is obtained from the Black-Box Model to determine whether the transformed input is drawn from in-distribution. We empirically show that our method has an advantage in generalization to geometric transformations and sample efficiency.

  • REST: Performance Improvement of a Black Box Model via RL-based Spatial Transformation
    arXiv: Learning, 2020
    Co-Authors: Jae Myung Kim, Hyungjin Kim, Chanwoo Park, Jungwoo Lee
    Abstract:

    In recent years, deep neural networks (DNN) have become a highly active area of research, and shown remarkable achievements on a variety of computer vision tasks. DNNs, however, are known to often make overconfident yet incorrect predictions on out-of-distribution samples, which can be a major obstacle to real-world deployments because the training dataset is always limited compared to diverse real-world samples. Thus, it is fundamental to provide guarantees of robustness to the distribution shift between training and test time when we construct DNN Models in practice. Moreover, in many cases, the deep learning Models are deployed as black boxes and the performance has been already optimized for a training dataset, thus changing the black box itself can lead to performance degradation. We here study the robustness to the geometric transformations in a specific condition where the Black-Box image classifier is given. We propose an additional learner, \emph{REinforcement Spatial Transform learner (REST)}, that transforms the warped input data into samples regarded as in-distribution by the Black-Box Models. Our work aims to improve the robustness by adding a REST module in front of any black boxes and training only the REST module without retraining the original black box Model in an end-to-end manner, i.e. we try to convert the real-world data into training distribution which the performance of the Black-Box Model is best suited for. We use a confidence score that is obtained from the Black-Box Model to determine whether the transformed input is drawn from in-distribution. We empirically show that our method has an advantage in generalization to geometric transformations and sample efficiency.

Torbjorn Wigren - One of the best experts on this subject based on the ideXlab platform.

J. Prat Goma - One of the best experts on this subject based on the ideXlab platform.

K. Ghafoor - One of the best experts on this subject based on the ideXlab platform.

  • Infusing domain knowledge in AI-based "black box" Models for better explainability with application in bankruptcy prediction.
    arXiv: Artificial Intelligence, 2019
    Co-Authors: Rabiul Islam, William Eberle, Sid C Bundy, K. Ghafoor
    Abstract:

    Although "black box" Models such as Artificial Neural Networks, Support Vector Machines, and Ensemble Approaches continue to show superior performance in many disciplines, their adoption in the sensitive disciplines (e.g., finance, healthcare) is questionable due to the lack of interpretability and explainability of the Model. In fact, future adoption of "black box" Models is difficult because of the recent rule of "right of explanation" by the European Union where a user can ask for an explanation behind an algorithmic decision, and the newly proposed bill by the US government, the "Algorithmic Accountability Act", which would require companies to assess their machine learning systems for bias and discrimination and take corrective measures. Top Bankruptcy Prediction Models are A.I.-based and are in need of better explainability -the extent to which the internal working mechanisms of an AI system can be explained in human terms. Although explainable artificial intelligence is an emerging field of research, infusing domain knowledge for better explainability might be a possible solution. In this work, we demonstrate a way to collect and infuse domain knowledge into a "black box" Model for bankruptcy prediction. Our understanding from the experiments reveals that infused domain knowledge makes the output from the black box Model more interpretable and explainable.