Minoru ASADA Masahiro KIMURA Yoshiaki SHIRAI
Integration of 2
Mun-Ho JEONG Yoshinori KUNO Nobutaka SHIMADA Yoshiaki SHIRAI
We present a method for recognition of two-hand gestures. Two-hand gestures include fine-grain descriptions of hands under a complicated background, and have complex dynamic behaviors. Hence, assuming that two-hand gestures are an interacting process of two hands whose shapes and motions are described by switching linear dynamics, we propose a coupled switching linear dynamic model to capture interactions between both hands. The parameters of the model are learned via EM algorithm using approximate computations. Recognition is performed by selection of the model with maximum likelihood out of a few learned models during tracking. We confirmed the effectiveness of the proposed model in tracking and recognition of two-hand gestures through some experiments.
Yoshiaki SHIRAI Tsuyoshi YAMANE Ryuzo OKADA
This paper describes methods of tracking of moving objects in a cluttered background by integrating optical flow, depth data, and/or uniform brightness regions. First, a basic method is introduced which extracts a region with uniform optical flow as the target region. Then an extended method is described in which optical flow and depth are fused. A target region is extracted by Baysian inference in term of optical flow, depth and the predicted target location. This method works only for textured objects because optical flow or depth are extracted for textured objects. In order to solve this problem, uniform regions in addition to the optical flow are used for tracking. Realtime human tracking is realized for real image sequences by using a real time processor with multiple DSPs.
Daiki ITO Kenta NOMURA Masaki KAMIZONO Yoshiaki SHIRAISHI Yasuhiro TAKANO Masami MOHRI Masakatu MORII
Cyber attacks targeting specific victims use multiple intrusion routes and various attack methods. In order to combat such diversified cyber attacks, Threat Intelligence is attracting attention. Attack activities, vulnerability information and other threat information are gathered, analyzed and organized in threat intelligence and it enables organizations to understand their risks. Integrated analysis of the threat information is needed to compose the threat intelligence. Threat information can be found in incident reports published by security vendors. However, it is difficult to analyze and compare their reports because they are described in various formats defined by each vendor. Therefore, in this paper, we apply a modeling framework for analyzing and deriving the relevance of the reports from the views of similarity and relation between the models. This paper presents the procedures of modeling incident information described in the reports. Moreover, as case studies, we apply the modeling method to some actual incident reports and compare their models.
Haisong GU Yoshiaki SHIRAI Minoru ASADA
This paper presents a method for spatial and temporal segmentation of long image sequences which include multiple independently moving objects, based on the Minimum Description Length (MDL) principle. By obtaining an optimal motion description, we extract spatiotemporal (ST) segments in the image sequence, each of which consists of edge segments with similar motions. First, we construct a family of 2D motion models, each of which is completely determined by its specified set of equations. Then, based on these sets of equations we formulate the motion description length in a long sequence. The motion state of one object at one moment is determined by finding the model with shortest description length. Temporal segmentation is carried out when the motion state is found to have changed. At the same time, the spatial segmentation is globally optimized in such a way that the motion description of the entire scene reaches a minimum.
Youji FUKUTA Yoshiaki SHIRAISHI Masakatu MORII
A nonlinear combiner random number generator is a general keystream generator for certain stream ciphers. The generator is composed of several linear feedback shift registers and a nonlinear function; the output is used as a keystream. A fast correlation attack is a typical attack for such keystream generators. Mihaljevi, Fossorier, and Imai have proposed an improved fast correlation attack. The attack is based on error correction of information bits only in the corresponding binary linear block code; APP threshold decoding is employed for the error correction procedure. In this letter, we propose a method which improves the success rate of their attacks with similar complexity. The method adds some intentional error to original parity check equations. Those equations are then used in APP threshold decoding.
Jun MIURA Tsuyoshi KANDA Shusaku NAKATANI Yoshiaki SHIRAI
This paper presents an active vision system for on-line traffic sign recognition. The system is composed of two cameras, one is equipped with a wide-angle lens and the other with a telephoto lens, and a PC with an image processing board. The system first detects candidates for traffic signs in the wide-angle image using color, intensity, and shape information. For each candidate, the telephoto-camera is directed to its predicted position to capture the candidate in a larger size in the image. The recognition algorithm is designed by intensively using built-in functions of an off-the-shelf image processing board to realize both easy implementation and fast recognition. The results of on-road experiments show the feasibility of the system.
Shohei KAKEI Masami MOHRI Yoshiaki SHIRAISHI Masakatu MORII
TPM-embedded devices can be used as authentication tokens by issuing certificates to signing keys generated by TPM. TPM generates Attestation Identity Key (AIK) and Binding Key (BK) that are RSA keys. AIK is used to identify TPM. BK is used to encrypt data so that specific TPM can decrypt it. TPM can use for device authentication by linking a SSL client certificate to TPM. This paper proposes a method of an AIK certificate issuance with OpenID and a method of the SSL client certificate issuance to specific TPM using AIK and BK. In addition, the paper shows how to implement device authentication system using the SSL client certificate related to TPM.
Hsiao-Jing CHEN Yoshiaki SHIRAI Minoru ASADA
A method for detecting multiple rigid motions in images from an optical flow field obtained with multi-scale, multi-orientation filters is proposed. Convolving consecutive gray scale images with a set of eight orientation-selective spatial Gaussian filters yields eight gradient constraint equations for the two components of a flow vector at every location. The flow vector and an uncertainty measure are obtained from these equations. In the neighborhood of motion boundary, the uncertainty of the flow vectors increase. By using multiple sets of filters of different scales, multiple flow vectors are obtained at every location, from which the one with minimal uncertainty measure is selected. The obtained flow field is then segmented in order to solve the aperture problem and to remove noise without blurring discontinuity in the flow field. Discontinuities are first detected as those locations where flow vectors have relatively larger uncertainty measures. Then similar flow vectors are gouped into regions. By modeling flow vectors, regions are merged to form segments each of which belongs to a planar patch of a rigid object in the scene.
Terence Chek Hion HENG Yoshinori KUNO Yoshiaki SHIRAI
Presently, mobile robots are navigated by means of a number of methods, using navigating systems such as the sonar-sensing system or the visual-sensing system. These systems each have their strengths and weaknesses. For example, although the visual system enables a rich input of data from the surrounding environment, allowing an accurate perception of the area, processing of the images invariably takes time. The sonar system, on the other hand, though quicker in response, is limited in terms of quality, accuracy and range of data. Therefore, any navigation methods that involves only any one system as the primary source for navigation, will result in the incompetency of the robot to navigate efficiently in a foreign, slightly-more-complicated-than-usual surrounding. Of course, this is not acceptable if robots are to work harmoniously with humans in a normal office/laboratory environment. Thus, to fully utilise the strengths of both the sonar and visual sensing systems, this paper proposes a fusion of navigating methods involving both the sonar and visual systems as primary sources to produce a fast, efficient and reliable obstacle-avoiding and navigating system. Furthermore, to further enhance a better perception of the surroundings and to improve the navigation capabilities of the mobile robot, active sensing modules are also included. The result is an active sensor fusion system for the collision avoiding behaviour of mobile robots. This behaviour can then be incorporated into other purposive behaviours (eg. Goal Seeking, Path Finding, etc. ). The validity of this system is also shown in real robot experiments.
Kenta NOMURA Masami MOHRI Yoshiaki SHIRAISHI Masakatu MORII
We focus on the construction of the digital signature scheme for local broadcast, which allows the devices with limited resources to securely transmit broadcast message. A multi-group authentication scheme that enables a node to authenticate its membership in multi verifiers by the sum of the secret keys has been proposed for limited resources. This paper presents a transformation which converts a multi-group authentication into a multi-group signature scheme. We show that the multi-group signature scheme converted by our transformation is existentially unforgeable against chosen message attacks (EUF-CMA secure) in the random oracle model if the multi-group authentication scheme is secure against impersonation under passive attacks (IMP-PA secure). In the multi-group signature scheme, a sender can sign a message by the secret keys which multiple certification authorities issue and the signature can validate the authenticity and integrity of the message to multiple verifiers. As a specific configuration example, we show the example in which the multi-group signature scheme by converting an error correcting code-based multi-group authentication scheme.
High variability of object features and bad class separation of objects are the main causes for the difficulties encountered during the interpretation of ground-level natural scenes. For coping with these two problems we propose a method which extracts those regions that can be segmented and immediately recognized with sufficient reliability (core regions) in the first stage, and later try to extend these core regions up to their real object boundaries. The extraction of reliable core regions is generally difficult to achieve. Instead of using fixed sets of features and fixed parameter settings, our method employs multiple local features (including textural features) and multiple parameter settings. Not all available features may yield useful core regions, but those core regions that are extracted from these multiple features make a cntributio to the reliability of the objects they represent. The extraction mechanism computes multiple segmentations of the same object from these multiple features and parameter settings, because it is not possible to extract such regions uniquely. Then those regions are extracted which satisfy the constraints given by knowledge about the objects (shape, location, orientation, spatial relationships). Several spatially overlapping regions are combined. Combined regions obtained for several features are integrated to form core regions for the given object calss.
Mun-Ho JEONG Yoshinori KUNO Nobutaka SHIMADA Yoshiaki SHIRAI
We present a method to track and recognize shape-changing hand gestures simultaneously. The switching linear model using active contour model well corresponds to temporal shapes and motions of hands. However, inference in the switching linear model is computationally intractable, and therefore the learning process cannot be performed via the exact EM (Expectation Maximization) algorithm. Thus, we present an approximate EM algorithm using a collapsing method in which some Gaussians are merged into a single Gaussian. Tracking is performed through the forward algorithm based on Kalman filtering and the collapsing method. We also present a regularized smoothing, which plays a role of reducing jump changes between the training sequences of shape vectors representing complex-variable hand shapes. The recognition process is performed by the selection of a model with the maximum likelihood from some trained models while tracking is being performed. Experiments for several shape-changing hand gestures are demonstrated.
Toshihiro OHIGASHI Yoshiaki SHIRAISHI Masakatu MORII
In a key scheduling algorithm (KSA) of stream ciphers, a secret key is expanded into a large initial state. An internal state reconstruction method is known as a general attack against stream ciphers; it recovers the initial state from a given pair of plaintext and ciphertext more efficiently than exhaustive key search. If the method succeeds, then it is desirable that the inverse of KSA is infeasible in order to avoid the leakage of the secret key information. This paper shows that it is easy to compute a secret key from an initial state of RC4. We propose a method to recover an -bit secret key from only the first bits of the initial state of RC4 using linear equations with the time complexity less than that of one execution of KSA. It can recover the secret keys of which number is 2103.6 when the size of the secret key is 128 bits. That is, the 128-bit secret key can be recovered with a high probability when the first 128 bits of the initial state are determined using the internal state reconstruction method.
Haruka ITO Masanori HIROTOMO Youji FUKUTA Masami MOHRI Yoshiaki SHIRAISHI
Recently, IoT compatible products have been popular, and various kinds of things are IoT compliant products. In these devices, cryptosystems and authentication are not treated properly, and security measures for IoT devices are not sufficient. Requirements of authentication for IoT devices are power saving and one-to-many communication. In this paper, we propose a zero-knowledge identification scheme using LDPC codes. In the proposed scheme, the zero-knowledge identification scheme that relies on the binary syndrome decoding problem is improved and the computational cost of identification is reduced by using the sparse parity-check matrix of the LDPC codes. In addition, the security level, computational cost and safety of the proposed scheme are discussed in detail.
Yoshiaki SHIRAISHI Toshihiro OHIGASHI Masakatu MORII
Knudsen et al. proposed an efficient method based on a tree-search algorithm with recursive process for reconstructing the internal state of RC4 stream cipher. However, the method becomes infeasible for word size n > 5 because its time complexity to reconstruct the internal state is too large. This letter proposes a more efficient method than theirs. Our method can reconstruct the internal state by using the pre-known internal-state entries, which are fewer than their method.
Yoshiaki SHIRAISHI Masaki KAMIZONO Masanori HIROTOMO Masami MOHRI
In the case of drive-by download attacks, most malicious web sites identify the software environment of the clients and change their behavior. Then we cannot always obtain sufficient information appropriate to the client organization by automatic dynamic analysis in open services. It is required to prepare for expected incidents caused by re-accessing same malicious web sites from the other client in the organization. To authors' knowledge, there is no study of utilizing analysis results of malicious web sites for digital forensic on the incident and hedging the risk of expected incident in the organization. In this paper, we propose a system for evaluating the impact of accessing malicious web sites by using the results of multi-environment analysis. Furthermore, we report the results of evaluating malicious web sites by the multi-environment analysis system, and show how to utilize analysis results for forensic analysis and risk hedge based on actual cases of analyzing malicious web sites.
Ryusei NAGASAWA Keisuke FURUMOTO Makoto TAKITA Yoshiaki SHIRAISHI Takeshi TAKAHASHI Masami MOHRI Yasuhiro TAKANO Masakatu MORII
The Topics over Time (TOT) model allows users to be aware of changes in certain topics over time. The proposed method inputs the divided dataset of security blog posts based on a fixed period using an overlap period to the TOT. The results suggest the extraction of topics that include malware and attack campaign names that are appropriate for the multi-labeling of cyber threat intelligence reports.
Kang-Hyun JO Kentaro HAYASHI Yoshinori KUNO Yoshiaki SHIRAI
This paper presents a vision-based human interface system that enables a user to move a target object in a 3D CG world by moving his hand. The system can interpret hand motions both in a frame fixed in the world and a frame attached to the user. If the latter is chosen, the user can move the object forward by moving his hand forward even if he has changed his body position. In addition, the user does not have to keep in mind that his hand is in the camera field of view. The active camera system tracks the user to keep him in its field of view. Moreover, the system does not need any camera calibration. The key for the realization of the system with such features is vision algorithms based on the multiple view affine invariance theory. We demon-strate an experimental system as well as the vision algorithms. Human operation experiments show the usefulness of the system.
Hsiao-Jing CHEN Yoshiaki SHIRAI
A method is presented to perform image segmentation by accumulatively observing apparent motion in a long image sequence of a dynamic scene. In each image in the sequence, locations are grouped into small patches of approximately uniform optical flow. To reduce the noise in computed flow vectors, a local image motion vector of each patch is computed by averaging flow vectors in the corresponding patches in several images. A segment contains patches belonging to the same 3-D plane in the scene. Initial segments are obtained in the image, and then an attempt to merge or split segments is iterated to update the segments. In order to remove inherent ambiguities in motion-based segmentation, temporal coherence between the local image motion of a patch and the apprent motion of every plane is investigated over long time. In each image, a patch is grouped into the segment of the plane whose apparent motion is temporally most coherent with the local image motion of the patch. When apparent motions of two planes are temporally incoherent, segments of the planes are retained as individual ones.