International Institute of Information Technology, Hyderabad

About: International Institute of Information Technology, Hyderabad is a education organization based out in Hyderabad, India. It is known for research contribution in the topics: Computer science & Authentication. The organization has 2048 authors who have published 3677 publications receiving 45319 citations. The organization is also known as: IIIT Hyderabad & International Institute of Information Technology (IIIT).

Realtime multibody visual SLAM with a smoothly moving monocular camera

Abstract: This paper presents a realtime, incremental multibody visual SLAM system that allows choosing between full 3D reconstruction or simply tracking of the moving objects. Motion reconstruction of dynamic points or objects from a monocular camera is considered very hard due to well known problems of observability. We attempt to solve the problem with a Bearing only Tracking (BOT) and by integrating multiple cues to avoid observability issues. The BOT is accomplished through a particle filter, and by integrating multiple cues from the reconstruction pipeline. With the help of these cues, many real world scenarios which are considered unobservable with a monocular camera is solved to reasonable accuracy. This enables building of a unified dynamic 3D map of scenes involving multiple moving objects. Tracking and reconstruction is preceded by motion segmentation and detection which makes use of efficient geometric constraints to avoid difficult degenerate motions, where objects move in the epipolar plane. Results reported on multiple challenging real world image sequences verify the efficacy of the proposed framework.

A Provably Secure and Lightweight Anonymous User Authenticated Session Key Exchange Scheme for Internet of Things Deployment

Abstract: With the ever increasing adoption rate of Internet-enabled devices [also known as Internet of Things (IoT) devices] in applications such as smart home, smart city, smart grid, and healthcare applications, we need to ensure the security and privacy of data and communications among these IoT devices and the underlying infrastructure. For example, an adversary can easily tamper with the information transmitted over a public channel, in the sense of modification, deletion, and fabrication of data-in-transit and data-in-storage. Time-critical IoT applications such as healthcare may demand the capability to support external parties (users) to securely access IoT data and services in real-time. This necessitates the design of a secure user authentication mechanism, which should also allow the user to achieve security and functionality features such as anonymity and un-traceability. In this paper, we propose a new lightweight anonymous user authenticated session key agreement scheme in the IoT environment. The proposed scheme uses three-factor authentication, namely a user’s smart card, password, and personal biometric information. The proposed scheme does not require the storing of user specific information at the gateway node. We then demonstrate the proposed scheme’s security using the broadly accepted real-or-random (ROR) model, Burrows–Abadi–Needham (BAN) logic, and automated validation of Internet security protocols and applications (AVISPAs) software simulation tool, as well as presenting an informal security analysis to demonstrate its other features. In addition, through our simulations, we demonstrate that the proposed scheme outperforms existing related user authentication schemes, in terms of its security and functionality features, and computation costs.

Generalized RBF feature maps for Efficient Detection

Abstract: Kernel methods yield state-of-the-art performance in certain applications such as image classification and object detection. However, large scale problems require machine learning techniques of at most linear complexity and these are usually limited to linear kernels. This unfortunately rules out gold-standard kernels such as the generalized RBF kernels (e.g. exponential-c 2 ). Recently, Maji and Berg [13] and Vedaldi and Zisserman [20] proposed explicit feature maps to approximate the additive kernels (intersection, c 2 , etc.) by linear ones, thus enabling the use of fast machine learning technique in a non-linear context. An analogous technique was proposed by Rahimi and Recht [14] for the translation invariant RBF kernels. In this paper, we complete the construction and combine the two techniques to obtain explicit feature maps for the generalized RBF kernels. Furthermore, we investigate a learning method using l 1 regularization to encourage sparsity in the final vector representation, and thus reduce its dimension. We evaluate this technique on the VOC 2007 detection challenge, showing when it can improve on fast additive kernels, and the trade-offs in complexity and accuracy.

KameleonFuzz: evolutionary fuzzing for black-box XSS detection

Abstract: Fuzz testing consists in automatically generating and sending malicious inputs to an application in order to hopefully trigger a vulnerability. Fuzzing entails such questions as: Where to fuzz? Which parameter to fuzz? Where to observe its effects?In this paper, we specifically address the questions: How to fuzz a parameter? How to observe its effects? To address these questions, we propose KameleonFuzz, a black-box Cross Site Scripting (XSS) fuzzer for web applications. KameleonFuzz can not only generate malicious inputs to exploit XSS, but also detect how close it is revealing a vulnerability. The malicious inputs generation and evolution is achieved with a genetic algorithm, guided by an attack grammar. A double taint inference, up to the browser parse tree, permits to detect precisely whether an exploitation attempt succeeded.Our evaluation demonstrates no false positives and high XSS revealing capabilities: KameleonFuzz detects several vulnerabilities missed by other black-box scanners.

Question Generation from Paragraphs at UPenn: QGSTEC System Description

Abstract: This paper describes the question generation system devel- oped at UPenn for QGSTEC, 2010. The system uses predicate argument structures of sentences along with semantic roles for the question gener- ation task from paragraphs. The semantic role labels are used to identify relevant parts of text before forming questions over them. The generated questions are then ranked to pick nal six best questions.