Thesis (M.S.)--Rochester Institute of Technology, 2010. / Typescript. Includes bibliographical references (leaves 57-58).

Thesis (Ph.D)--Computing, Georgia Institute of Technology, 2010. / Committee Chair: Boldreva, Alexandra; Committee Member: Ahamad, Mustaque; Committee Member: Randall, Dana; Committee Member: Tetali, Prasad; Committee Member: Traynor, Patrick. Part of the SMARTech Electronic Thesis and Dissertation Collection.

The explosive growth of multimedia data in online media repositories and social networks has led to the high demand of fast and accurate services for large-scale multimedia retrieval. Hashing, due to its effectiveness in coding high-dimensional data into a low-dimensional binary space, has been considered to be effective for the retrieval application. Despite the progress that has been made recently, how to learn the optimal hashing models which can make the best trade-off between the retrieval efficiency and accuracy remains to be open research issues. This thesis research aims to develop hashing models which are effective for image and video retrieval. An unsupervised hashing model called APHash is first proposed to learn hash codes for images by exploiting the distribution of data. To reduce the underlying computational complexity, a methodology that makes use of an asymmetric similarity matrix is explored and found effective. In addition, the deep learning approach to learn hash codes for images is also studied. In particular, a novel deep model called DeepQuan which tries to incorporate product quantization methods into an unsupervised deep model for the learning. Other than adopting only the quadratic loss as the optimization objective like most of the related deep models, DeepQuan optimizes the data representations and their quantization codebooks to explores the clustering structure of the underlying data manifold where the introduction of a weighted triplet loss into the learning objective is found to be effective. Furthermore, the case with some labeled data available for the learning is also considered. To alleviate the high training cost (which is especially crucial given a large-scale database), another hashing model named Similarity Preserving Deep Asymmetric Quantization (SPDAQ) is proposed for both image and video retrieval where the compact binary codes and quantization codebooks for all the items in the database can be explicitly learned in an efficient manner. All the aforementioned hashing methods proposed have been rigorously evaluated using benchmark datasets and found to outperform the related state-of-the-art methods.

This thesis is concerned with the design and analysis of practical provably-secure encryption schemes. We give several results that include new schemes with attractive tradeoffs between efficiency and security and new techniques for analyzing existing schemes. Our results are divided into three chapters, which we summarize below. The Twin Diffie-Hellman Problem. We describe techniques for analyzing encryption schemes based on the hardness of Diffie-Hellman-type problems. We apply our techniques to several specific cases of encryption, including identity-based encryption, to design a collection of encryption schemes that offer improved tradeoffs between efficiency and evidence for security over similar schemes. In addition to offering quantitative advantages over prior work in this area, our technique also simplifies security proofs for these types of encryption schemes. Our main tool in this chapter is the notion of Twin Diffie-Hellman Problems, which provide an intermediate step for organizing security reductions and reveal very simple variants of known schemes with correspondingly simple, but non-obvious, analyses. Non-Malleable Hash Functions. We consider security proofs for encryption that are carried out in the random oracle model, where one declares that a scheme's hash functions are ``off limits' for an attacker in order to make a proof go through. Such proofs leave some doubt as to the security of the scheme in practice, when attackers are free to exploit weaknesses in the hash functions. A particular concern is that a scheme may be insecure in practice no matter what very strong security properties its real hash functions satisfy. We address this doubt for an encryption scheme of Bellare and Rogaway by showing that, using appropriately strong hash functions, this scheme's hash functions can be partially instantiated in a secure way.

Thesis (M.S.)--Rochester Institute of Technology, 2008. / Typescript. Includes bibliographical references (leaf 49).

Thesis (M.S.)--Rochester Institute of Technology, 1987. / Typescript. Includes bibliographical references (leaves 137-144).

Thesis (M.Eng.(Electronic Engineering))--University of Pretoria, 1999. / Summaries in Afrikaans and English. Includes bibliographical references.

Thesis (M.S.)--Rochester Institute of Technology, 2009. / Typescript. Includes bibliographical references.

Orientador: Ricardo Dahab / Dissertação (mestrado profissional) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-09T00:39:10Z (GMT). No. of bitstreams: 1 Tavares_PauloHenrique_M.pdf: 612792 bytes, checksum: 34039a441661bcdbc5f686566d558fae (MD5) Previous issue date: 2006 / Resumo: Nos últimos anos, a quantidade de dispositivos móveis tem crescido dramaticamente assim como a complexidade das aplicações que os usuários desejam executar neles. Ao mesmo tempo, a preocupação com a segurança do grande público também tem aumentado, criando uma demanda maior por aplicações criptográficas, como assinaturas digitais, que dependem de funções de resumo (hash) criptográfico. Neste contexto tornou-se importante estudar o desempenho de funções de resumo nesta nova geração de processadores, desenvolvidos para estes dispositivos. Neste trabalho estudamos a família de funções de resumo SHA (Secure Hash Algorithm) e Whirlpool, algumas de suas implementações, as características dos processadores Intel XScale que podem ser usadas para melhorar o desempenho de tais funções, com atenção especial para as novas extensões Wireless MMX. Também aplicamos algumas dessas técnicas e apresentamos os resultados dos testes de desempenho executados / Abstract: In recent years, the number of mobile devices has grown dramatically and so has the complexity of applications their users wish to run. At the same time, security concerns of the general public have also increased, creating a greater demand for cryptographic applications such as digital signatures, which use hash functions. In this context it has become very important to study the performance of hash functions on the new generation of processors developed for these devices. In this work we study the SHA (Secure Hash Algorithm) family of hash functions and some of their implementations, the Intel XScale processors characteristics that can be used to improve the performance of those functions, with special attention to the new Wireless MMX extensions. We also applied some of these techniques and report the results of the performance tests executed. / Mestrado / Engenharia de Computação / Mestre Profissional em Computação

Orientador: Julio César López Hernández / Dissertação (mestrado) - Universidade Estadual de Campinas, Instituto de Computação / Made available in DSpace on 2018-08-18T13:36:05Z (GMT). No. of bitstreams: 1 Oliveira_ThomazEduardodeFigueiredo_M.pdf: 4175073 bytes, checksum: 14d147ca37955c85736d05e60182a583 (MD5) Previous issue date: 2011 / Resumo: Os algoritmos de resumo criptográfico são uma importante ferramenta usada em muitas aplicações para o processamento seguro e eficiente de informações. Na década de 2000, sérias vulnerabilidades encontradas em funções de resumo tradicionais, como o SHA-1 e o MD5, levou a comunidade a repensar o desenvolvimento da criptanálise destes algoritmos e projetar novas estratégias para a sua construção. Como resultado, o instituto NIST anunciou em novembro de 2007 um concurso público para o desenvolvimento de um novo padrão de funções de resumo, o SHA-3, contando com a participação de autores de todo o mundo. Esta dissertação foca nos aspectos da implementação em software de alguns algoritmos submetidos no concurso SHA-3, buscando compreender a forma como os autores desenvolveram a questão do custo computacional de seus projetos em diversas plataformas, além de entender os novos paradigmas de implementação introduzidos pela tecnologia presente nos processadores atuais. Como consequência, propusemos novas técnicas algorítmicas para a implementação em software de alguns algoritmos, como o Luffa e o Keccak, levando aos mesmos melhorias significativas de desempenho / Abstract: Hash algorithms are an important tool of cryptography used in many applications for secure and efficient information processing. During the 2000 decade, serious vulnerabilities found at some traditional hash functions like SHA-1 and MD5 prompted the cryptography community to review the advances in the cryptanalysis of these algorithms and their design strategies. As a result, on November, 2007, NIST announced a public competition to develop a new cryptographic hash function, the SHA-3, which involved competitors throughout the world. This work focuses on the software implementation aspects of some of the SHA-3 submitted algorithms, seeking to comprehend how the authors resolved the computational cost issues at distinct platforms and to understand the new paradigms introduced by the present processors technology. As a consequence, we proposed new algorithmic techniques for the software implementation of Luffa and Keccak hash algorithms, improving their performance significantly / Mestrado / Teoria da Computação / Mestre em Ciência da Computação