Year-2016
http://repository.iiitd.edu.in/xmlui/handle/123456789/389
2024-01-30T10:47:10ZSparse recovery techniques for hyperspectral imaging
http://repository.iiitd.edu.in/xmlui/handle/123456789/495
Sparse recovery techniques for hyperspectral imaging
Aggarwal, Hemant Kumar; Majumdar, Angshul (Advisor)
Human vision is a powerful imaging system that can capture and interpret light
energy coming from different sources although it is limited to visible light. There are
various applications such as face recognition, medical imaging, agriculture, geology,
surveillance, etc. that benefits by imaging several bands of the electromagnetic spectrum
outside the visible range. The hyperspectral imaging techniques are capable of
capturing hundreds of bands of the electromagnetic spectrum and thus, can be considered
as the generalization of color imaging.
The focus of this dissertation is on modeling hyperspectral imaging problems as
linear inverse problems and solving them by exploiting inherent data properties. These
imaging problems often form an underdetermined system of the linear equations having
infinitely many solutions; therefore, additional constraints based on prior knowledge
about data can help in determining the solution uniquely.
This work aims at developing multispectral image acquisition and reconstruction
techniques such that minimal changes are required in the hardware of compact digital
cameras. A uniform multispectral filter array design has been proposed that satisfy
both spatial consistency and spectral uniformity requirements. Based on proposed
filter array pattern, an efficient demosaicing algorithm has been proposed to reconstruct
the full multispectral image from severely under-sampled raw image such that
reconstructed image has good visual quality.
This work also focuses on hyperspectral denoising problem. Anovel spatio-spectral
total-variation model has been proposed that gives a sparser representation of the
sorted discrete gradient coefficients as compared to the band by band hyperspectral
total-variation model. A general additive noise model was considered that accounts
for not only Gaussian noise but also the sparse noise that includes impulse noise
and line strips. The resulting optimization problem was solved using augmented-
Lagrangian like the split-Bregman algorithm.
Another problem discussed in this work is the hyperspectral unmixing problem
that is related to blind source separation problem in signal processing. A joint-sparse
model along with total variation in the general noise model framework has been considered
in formulating the problem as a linear sparse unmixing problem. Since a particular
endmember may be present at several locations, therefore, abundance maps
shows joint sparsity. Proposed joint-sparsity and total variation based unmixing algorithm
have been compared with several related unmixing algorithms to empirically
demonstrate its performance using visual quality as well as signal to noise ratio.
Further, A deep dictionary learning based approach has been proposed for hyperspectral
image classification problem. The learning proceeds in a greedy fashion,
therefore for each level we only need to learn a single layer of the dictionary. A comparative
study with deep belief network and stacked autoencoder based techniques
suggests that in the practical scenario, when the training data is limited, the proposed
method outperforms these more established tools.
2016-12-23T07:21:39ZAutomated methods for identity resolution across online social networks
http://repository.iiitd.edu.in/xmlui/handle/123456789/391
Automated methods for identity resolution across online social networks
Jain, Paridhi; Kumaraguru, Ponnurangam (Advisor)
Today, more than two hundred Online Social Networks (OSNs) exist where each OSN extends to offer distinct services to its users such as eased access to news or better business opportunities. To enjoy each distinct service, a user innocuously registers herself on multiple OSNs. For each OSN, she defines her identity with a different set of attributes, genre of content and friends to suit the purpose of using that OSN. Thus, the quality, quantity and veracity of the identity varies with the OSN. This results in dissimilar identities of the same user, scattered across Internet, with no explicit links directing to one another. These disparate unlinked identities worry various stakeholders. For instance, security practitioners find it difficult to verify attributes across unlinked identities; enterprises fail to create a holistic overview of their customers.
Research that finds and links disconnected identities of a user across OSNs is termed as identity resolution. Accessibility to unique and private attributes of a user like ‘email’ makes the task trivial, however in absence of such attributes, identity resolution is challenging. In this dissertation, we make an effort to leverage intelligent cues and patterns extracted from partially overlapping list of public attributes of compared identities. These patterns emerge due to consistent user behavior like sharing same mobile number, content or profile picture across OSNs. Translating these patterns into features, we devise novel heuristic, unsupervised and supervised frameworks to search and link user identities across social networks. Proposed search methods use an exhaustive set of public attributes looking for consistent behavior patterns and fetch correct identity of the searched user in the candidate set for an additional 13% users. An improvement on the proposed search mechanisms further optimizes time and space complexity. Suggested linking method compares past attribute value sets and correctly connect identities of an additional 48% users, earlier missed by literature methods that compare only current values. Evaluations on popular OSNs like Twitter, Instagram and Facebook prove significance and generalizability of the linking method.
Proposed search and linking methods are applicable to users that exhibit evolutionary and consistent behavior on OSNs. To understand the dynamics and reasons for such behavior, we conduct two independent in-depth studies. For user evolutionary behavior, specifically for username, we observe that username evolution leads to broken link (404 page) to a user profile. Yet, 10% of 8.7 million tracked Twitter users changed their username in two months. Investigation reveals that reasons to change include malign intentions like fraudulent username promotion and benign ones like express support to events. We believe that Twitter can monitor frequent username changes, derive malign intentions and suspend accounts if needed. Study of sharing information consistently across OSNs, e.g. mobile number, highlights why users share a personally identifiable information online and how can it be used with auxiliary information sources to derive details of a user.
In summary, this dissertation encashes previously unused public user information available on a
social network for identity resolution via novel methods. The thesis work makes following advancements: a) Propose search frameworks that aim to fetch correct identity of a user in the candidate set by searching with public and discriminative attributes, b) Propose a supervised classification framework for linking identities that compares respective attribute histories in situations where state-of-the-art methods fail to predict the link, c) Study username evolution on Twitter, and d) Study mobile number sharing behavior across OSNs. Proposed methods require no user authorization for data access, yet successfully leverage innocuous user public activity and details, find her accounts across OSNs and help stakeholders with better insights on user’s likings or her suspicious intentions.
2016-04-28T05:13:10ZAnalysis of block cipher constructions against biclique and multiset attacks
http://repository.iiitd.edu.in/xmlui/handle/123456789/390
Analysis of block cipher constructions against biclique and multiset attacks
Ghosh, Mohona; Sanadhya, Somitra Kumar (Advisor); Chang, Donghoon (Advisor)
Cryptographic protocols have been a cornerstone of secure communications among armed forces and diplomatic missions since time immemorial. With easy availability and low cost of computing facilities and Internet, the domain of cryptology has not only expanded to non-government uses but also in fulfilling the common needs of individuals. Block ciphers are the basic building blocks of most of today's deployed cryptography and are one of the most widely used cryptographic primitives. They play a crucial role in providing confidentiality of data transmitted over insecure communication channels - one of the fundamental goals of cryptography. Apart from it, block ciphers are also used to build other cryptographic mechanisms such as - Hash functions and Message Authentication Codes. Hence, it is crucial to ensure construction of a secure and robust block cipher design. To achieve so, it is imperative to analyze and evaluate the resistance of block ciphers against a variety of cryptanalytic attacks.
This thesis is devoted to the security analysis of block ciphers and block cipher based hash functions against some of the current state-of-the-art cryptanalytic techniques. We specifically focus on Biclique Cryptanalysis and Multiset Attacks in this work. We propose a new extension of biclique technique - termed as Star based Bicliques and use them to solve the problem of high data complexity usually associated with this technique. Further, we also employ the above cryptanalytic methods to provide the best attacks on few standardized block ciphers. Our cryptanalytic results are as follows:
1. We study biclique based key recovery attacks and _nd improvements that lower the attack costs compared to the original attack in [39]. These attacks are applied to full round AES-128 (10-rounds), AES-192 (12-rounds) and AES-256 (14-rounds) with interesting observations and results. As part of the results, we propose star-based bicliques which allow us to launch attacks
with the minimal data complexity in accordance with the unicity distance. Each attack requires just 2-3 known plaintexts with success probability 1.
2. We utilize the biclique based key recovery attacks to find second-preimages on AES based hashing modes. In our attacks, the initialization vector (IV) is a public constant that cannot be changed by the attacker. Under this setting, with message padding restrictions, the biclique trails constructed for key recovery attack in [39] cannot be utilized here. We construct new
biclique trails that satisfy the above restrictions and launch second preimage attacks on all 12 PGV hashing modes based on full round AES-128.
3. We investigate the security of Generalized Feistel Networks (GFNs) in known-key scenario. We apply a variant of biclique technique – termed as sliced biclique cryptanalysis on 4-branch, Type-2 Generalized Feistel Networks (GFNs) based hash functions to generate actual collisions. We further demonstrate the best 8-round collision attack on 4-branch, Type-2 based GFNs when the round function F is instantiated with double SP layers.
4. We analyze the security of Korean Encryption Standard ARIA against meet-in-the-middle attack model. We conduct multiset based key recovery attacks on 7 and 8-round ARIA-192 and ARIA-256 with improved time, memory and data complexities compared to [168]. While the previous attacks on ARIA could only recover some round keys, our attacks show the first recovery of the complete master secret key.
5. We analyze the security of recently announced Ukrainian Encryption Standard Kalyna against meet-in-the-middle attack model. We apply multiset attacks supplemented with further related advancements in this attack technique to recover the secret key from 9-round Kalyna-128/256 and Kalyna-256/512. This improves upon the previous best attack reported in [13] in terms of number of rounds attacked by 2.
In terms of either the attack complexity or the number of attacked rounds, the attacks presented in the thesis are better than any previously published cryptanalytic results for the block ciphers concerned.
2016-04-18T11:37:43Z