Saritha Arunkumar

Back to the future: A fully automatic method for robust age progression

It has been shown that significant age difference between a probe and gallery face image can decrease the matching accuracy. If the face images can be normalized in age, there can be a huge impact on the face verification accuracy and thus many novel applications such as matching drivers license, passport and visa images with the real persons images can be effectively implemented. Face progression can address this issue by generating a face image for a specific age. Many researchers have attempted to address this problem focusing on predicting older faces from a younger face. In this paper, we propose a novel method for robust and automatic face progression in totally unconstrained conditions. Our method takes into account that faces belonging to the same age-groups share age patterns such as wrinkles while faces across different age-groups share some common patterns such as expressions and skin colors. Given training images of K different age-groups the proposed method learns to recover K low-rank age and one low-rank common components. These extracted components from the learning phase are used to progress an input face to younger as well as older ages in bidirectional fashion. Using standard datasets, we demonstrate that the proposed progression method outperforms state-of-the-art age progression methods and also improves matching accuracy in a face verification protocol that includes age progression.

Global attestation of location in mobile devices

Location information in mobile devices are very important part of any location based transactions. The information can be faked and can be misrepresented for meeting specific requirements. A number of mechanisms have been used to ensure that the location information provided by the mobile device is accurate. In this paper, we introduce the notion of gathering evidences independently where each entity reports contacts with other entities in specific locations at specific times. Some of the reports may be not true and in order to scrutinize these, we introduce the global consistency check. This is mainly based on the model similar to the block chain model in Bitcoin. With a global consistency check we can ensure if a particular entity is being dishonest about the location information. We have used the EigenTrust and PeerTrust check methodologies to calculate global and personalised trust matrix while confirming attestation. The paper also shows the importance of global attestation scheme over local attestation.

Reasoning with streamed uncertain information from unreliable sources

We propose comprehensive framework where unstructured reports are streamed.Trustworthiness of the opinions are estimated before fusion.Conflicts are detected, resolved by analyzing evidence about reliability of sources.Implementation of the framework is presented with evaluation.Evaluation quantifies efficiency with respect to accuracy and overhead. Humans or intelligent software agents are increasingly faced with the challenge of making decisions based on large volumes of streaming information from diverse sources. Decision makers must process the observed information by inferring additional information, estimating its reliability and orienting it for decision-making. In this paper, we propose a stream-reasoning framework that achieves all these goals. While information is streamed as unstructured reports (e.g., text in natural language) from unreliable sources, our framework first converts it into a structured form using Controlled English and then it derives some facts that are useful for decision-making, and estimates the trust in these facts. Lastly, various facts are fused based on their trustworthiness. This process is totally undertaken on streaming information resulting in new facts being inferred from incoming information which immediately goes through trust assessment framework and trust is propagated to the inferred fact. In this paper, we propose a comprehensive framework where unstructured reports are streamed from heterogeneous and potentially untrustworthy information sources. These reports are processed to extract valuable uncertain information, which is represented using controlled natural language and subjective logic. Additional information is inferred using deduction and abduction operations over subjective opinions derived from the reports. Before fusing extracted and inferred opinions, the framework estimates trustworthiness of these opinions, detects conflicts between them, and resolve these conflicts by analysing evidence about the reliability of their sources. Lastly, we describe an implementation of the framework using International Technology Alliance (ITA) assets (Information Fabric Services and Controlled English Fact Store) and present an experimental evaluation that quantifies the efficiency with respect to accuracy and overhead of the proposed framework.

Learning information release policies for preventing intersection attacks

Location Based Services in the world of mobile devices has been used widely in all sectors and in various applications. It allows one to track the location, track services and also perfom other location based operations. Although its uses are very significant, the information related to location has opened up opportunities for adversary to misuse the mobile clients. This paper addresses one such problem with location information release and the problem addressed is mainly around Intersection Attacks. The two geo-spatial information over a period of time may be kept private but the time interval between the two specific time periods could lead to information leakage. This paper proposes two methodologies called “hierarchical signatures” and “Markov devision process” to mitigate intersection attacks. The paper also details the experimentation and results based on the tests done on two types of datasetc including reality mining datasets and telecommunication datasets.

Location attestation and access control for mobile devices using GeoXACML

Access control has been applied in various scenarios in the past for negotiating the best policy. Solutions with XACML for access control has been very well explored by research and have resulted in significant contributions to various sectors including healthcare. In controlling access to the sensitive data such as medical records, it is important to guarantee that the data is accessed by the right person for the right reason. Location of access requestor can be a good indication for his/her eligibility and reasons for accessing the data. To reason with geospatial information for access control, Geospatial XACML (eXtensible Access Control Markup Language) is proposed as a standard. However, there is no available implementation and architecture for reasoning with Geospatial XACML policies. This paper proposes to extend XACML with geohashing to implement geospatial policies. It also proposes an architecture for checking reliability of the geospatial information provided by clients. With a case study, we demonstrate how our framework can be used to control the privacy and data access of health service data in handheld devices.

Privacy enforcement through policy extension

Successful coalition operations require contributions from the coalition partners which might have hidden goals and desiderata in addition to the shared coalition goals. Therefore, there is an inevitable risk-utility trade-off for information producers due to the need-to-know vs. need-to-hide tension, which must take into account the trustworthiness of the other coalition partners. A balance is often achieved by deliberate obfuscation of the shared information. In this paper, we show how to integrate obfuscation capabilities within the current OASIS standard for access control policies, namely XACML.

GeoSpatial Access Control for Mobile Devices

Access control has been applied in various scenarios in the past for negotiating the best policy. Solutions with XACML for access control has been very well explored by research and have resulted in significant contributions to various sectors including healthcare. In controlling access to the sensitive data such as medical records, it is important to guarantee that the data is accessed by the right person for the right reason. Location of access requestor can be a good indication for his/her eligibility and reasons for accessing the data. To reason with geospatial information for access control, Geospatial XACML (Extensible Access Control Markup Language) is proposed as a standard. However, there is no available implementation and architecture for reasoning with Geospatial XACML policies. This paper propose to extend XACML with geohashing to implement geospatial policies. It also proposes an architecture for checking reliability of the geospatial information provided by clients. With a case study, we demonstrate how our framework can be used to control the privacy and data access of health service data in handheld devices.