Tata Consultancy Services Limited

Sachin Premsukh Lodha

Vijayanand Mahadeo Banahatti

Mangesh Sharad Gharote

Kumar Mansukhlal Vidhani

Manish Shukla

Sutapa Mondal

Arun Ramamurthy

Arun Kumar Jindal

Srinivasa Rao Chalamala

Shirish Subhash Karande

Gangadhara Reddy Sirigireddy

Saket Kumar Saurabh

Rohit Saxena

Rosni Kottekulam Vasu

Rajan Mindigal Alasingara Bhattachar

Ashim Roy

Purushotam Gopaldas Radadia

Sumesh Manjunath

Sumit Johri

Monika Sahu

Shree Nivas

Rahul Kumar

Nikhil Girish Patwardhan

Imtiyazuddin Shaik

Ajeet Kumar Singh

Rupali Kedar Kulkarni

Kishore Padmanabhan

Mandar Shrikant Kulkarni

Kanika Kalra

Anand Sriraman

Mayur Jain

Arijit Ukil

Mariswamy Girish Chandra

Krishna Rao Kakkirala

Meena Singh Dilip Thakur

Shubhro Shovan Roy

Joel Joseph

Pankaj Kumar Sahu

Akhil Anand Dixit

Vasudha Kumari

Harika Narumanchi

Vijayarangan Natarajan

Bala Mallikarjunarao Garlapati

Balakrishna Gudla

Santosh Kumar Jami

Shrikant Joshi

Nandita Babu

Rohit Gupta

Vigneswaran Ramachandran

Amol Rajendra Limaye

Sanjay Seetharaman

Kalyani Mashiwal

Rishabh Kumar

Harshal Tupsamudre

Surabhi Garg

Ram Kumar

Harshal Tupasamudre

Gurpriya Kaur Bhatia

Gokul Chettoor Jayakrishnan

Sanket Achal Sinha

Venkata Rajan Mindigal Alasingara Bhattachar

Vaibhav Harihar Agasti

Aishwarya Arun Shinde

Vidyadhar Rao

Shefali Soni

Payal Ashok Lathi

Rekha Chandrakant Pathak

Nikhil Pradeep Sambhus

Govind Vitthal Waghmare

Nitin Ganesh Phuke

Amit Prakash Jadhav

Dilys Thomas

Devangi Deveshkumar Vyas

Sandhya Sree Thaskani

Nakhil Girish Patwardhan

Iyengar Venkatachary Srinivasan

Akshay Baban Kamble

Aditya Ahuja

Shaik Imtiyazuddin

Imtiyazuddir Shaik

Rosni Kottekulamvasu

Gangadhara Sirigireddy Reddy

Vijayana Mahadeo Banahatti

Vidhani Kumar

State of the art code matching approaches have the disadvantage that they rely on the line numbers provided by source code and binary parsers to establish mapping and do not work since changes introduced by compiler may be much more complex. Some approaches do not work as the source code of application and its binary version may not share the vocabulary. Machine learning based techniques have the disadvantage that they require significant amount of training data, which may not be available in abundance. Method and system disclosed herein provide a mechanism matching score for each of a plurality of code fragments in the intermediate representation of the source code file for each of a plurality of binary fragments in the intermediate representation of the binary file.

Method and system for matching source code and binary code

This disclosure relates generally to method and system for providing data privacy in service operations. Identifying risk arising from processing of user request in service operations is time consuming and monitoring insider threats is a difficult task. The method includes receiving a user request for a service comprising a plurality of sensitive attributes and further a vulnerability rating is assigned to each sensitive attribute. To mitigate the risk, the method estimates a disclosure proportion for the plurality of sensitive attributes and a masking operation is performed. Further, a sensitivity score is computed to allocate the user request to an agent associated with an agent registry with enabled data privacy and minimal data exposure. The agent is monitored by computing an agent mis-usability score to assess an insider threat risk. Additionally, a feedback alert is notified to autotune the plurality of privacy settings.

Method and system for providing data privacy in service operations

The embodiments of present disclosure herein address the need of minimizing web services relocation and user centers reallocation to comply with data residency regulations and change in latency threshold for web services based on user demands. The method and system provide a framework that assists enterprises in migrating web services and user center allocation to different data centers with lower additional operational cost from its current configurations and minimal changes (migrations). In case of change in data regulations and invocation frequency from users demand, non-compliant users are allocated to compliant data centers with minimal changes in the original configuration. Though the key decision is to serve the customers effectively, web services need to be deployed across a finite number of servers, there are multiple sub-problems such as minimizing latency and reduction in operational cost that needs to be addressed.

System and method for web services relocation and users reallocation for data residency compliance

The present disclosure a method for data regulations-aware cloud storage and processing service allocation. Conventional approaches fail to address the technical problem of data placement for storage as well as processing, considering multiple criteria. Further, the conventional approaches fail to address compliance with data regulations, tier pricing policy for multiple Cloud Service Providers (CSPs) which impacts storage and processing center selection and constraint satisfaction. The present disclosure proposes a joint optimization model for the selection of storage and processing services from multiple cloud service providers, taking into practical consideration of data regulations and tiered pricing, which has not been addressed in the prior art. To solve this hard multi-objective combinatorial optimization problem, the present disclosure utilizes a cost-reduction-based algorithm for obtaining optimal solution.

Method and system for data regulations-aware cloud storage and processing service allocation

The present disclosure provides an efficient system for cancelable biometric template protection which is not available in the conventional systems. Initially, the system receives a biometric template from a user. The biometric template is one of, a face image, a fingerprint, an iris image and a palmprint. Further, a vector embedding is computed based on the biometric template using a pretrained neural network. After computing the vector embedding, a key based permutation is computed based on the vector embedding and a permutation key. The permutation key is generated based on an Identification number (ID) associated with the user using a random number based key generation technique. Finally, a protected biometric template is generated by computing a permuted embedding corresponding to the biometric template based on the key based permutation using a plurality of fully connected layers pretrained using a weight based center triplet loss function.

Method and system for generating protected biometric templates

Finding optimal solutions to Web Service Location Allocation Problem (WSLAP) using exhaustive algorithms and exact approaches is not practical. Computational time required to solve WSLAP using exact approaches increases exponentially with the problem size. The disclosure herein generally relates to service deployment, and, more particularly, to a method and system for web service location allocation and virtual machine deployment. The system identifies a plurality of web-services that are associated with the WSLAP and then decomposes the WSLAP to a plurality of sub-problems. For each sub-problem, the system determines at least one non-dominating solution, which are then merged to generate the solution for the WSLAP. The generated solution to the WSLAP can be used for perform Virtual Machine (VM) deployment under uncertainties, using a stochastic approach, wherein the uncertainties refer to dynamic change in requirements in terms of parameters such as but not limited to configuration, and cost.

Method and system for web service location allocation and virtual machine deployment

Several data breaches are occurring in organizations due to insecure handling security-sensitive data. Conventional methods utilize static analysis tools and fail to capture all security vulnerabilities. The present disclosure identifies a security vulnerability by analyzing a source code. Initially, a System Dependence Graph (SDG) associated with the source code is received. Forward slicing is performed on the SDG and a plurality of forward function nodes are obtained. A plurality of security parameters associated with the security-sensitive variable are obtained. A backward slicing is performed based on a plurality of security parameters to obtain a plurality of backward function nodes. Further, a plurality of common function nodes is obtained from the plurality of forward and the backward function nodes and utilized to generate a plurality of enumerated paths. The enumerated paths are evaluated to obtain a plurality of feasible paths and are further analyzed to identify security vulnerability.

Method and system for identifying security vulnerabilities

Existing data residency compliance techniques suffer from inherent drawbacks to discover the spread of data, understanding the data residency regulations and semantics behind them and most importantly placement of data in cloud datacenters such that it is data residency compliant. Embodiments herein provide a method and system for optimizing placement of data to a cloud datacenter complying data residency regulations. The system selects one serving cloud datacenter for a user center. The selection considers three conflicting objectives such as minimum data placement cost, provide good quality of service (i.e. latency) and to comply with data residency regulations. The system essentially covers data residency compliance problem in three phases namely, violation detection, decision support and recommendation. Herein, the system trades-offs latency with data placement cost. Further, the system considers user center location, determined violation of data residency regulations, cost of movement from one datacenter to another, and a predefined threshold latency.

System and method for data residency compliant data placement in cloud

This disclosure relates generally to data anonymization using clustering techniques. In Typically, data anonymization using global recoding can overgeneralize the data. However, preservation of information while anonymization the data is of equal importance as obscuring the relevant information that can be used by the attackers. The disclosed method and system utilized attribute taxonomy tree for generalization to optimize the generalization of the records. The disclosed method uses clustering-based approach and after clustering, each cluster is solved independently using ILP model for K-Anonymization. The ILP model is solved by generalizing the value of the attributes. Sometimes, even after clustering the number of possible patterns is large, thus the disclosed method generates patterns on the fly during multiple iterations.

System and method for data anonymization using optimization techniques

The disclosure relates to sequencing of asset segments of privacy policies. The asset segments are sequenced based on a set of constraints. In an embodiment the asset segments are sequenced using a set of pre-defined predecessors and a set of pre-defined successors of each asset segment through a feasible sequence generation technique and a sequence generation technique based on the constraints, wherein the constraints are preferences associated with the source entity and the target entity. Hence the disclosure bridges a communication gap between the source entity and the target entity by optimally displaying the most relevant privacy policy (mapped to the asset segments) based on the constraints associated with the source entity and the target entity. Further the disclosed system also determines a violation factor that represents a conflict between the preferences associated with the source entity and the target entity.

Method and system for sequencing asset segments of privacy policy

This disclosure relates generally to system and method for assessing insider influence on enterprise assets. Existing work focuses on the detection of insider threat and does not consider the influence of an insider on their peers and subordinates. The present disclosure aggregates and preprocesses the enterprise data specific to the individuals received from various sources, and further creates an enterprise graph between entities. Weights of every edge connected between any two entities in the enterprise graph is then calculated. Community of the individuals are detected wherein, relevant insider(s) are identified, and susceptibility of the individuals for probable influence by relevant insider(s) based on the analysis scenarios(s) is calculated. Paths taken by the relevant insider(s) is calculated for estimating probability of data loss. The present disclosure identifies the assets which are under possible threat from the relevant insider(s), obtains cumulative risk associated with the enterprise and generates an analysis report accordingly.

System and method for assessing insider influence on enterprise assets

This disclosure relates generally to data anonymization and more particular y risk-aware data anonymization. Conventional data anonymization systems either replace PII/sensitive attributes with random values or shuffles them, that causes huge data distortion affecting the data utility. The goal of publishing data is best achieved when privacy is balanced with utility of data, Moreover, to ensure privacy, assessing the risk of disclosure is important. The proposed system provides a pipeline for analysis of data patterns to understand the associated risk level of re-identification of records. Further, based on the identified risks with the records the system anonymizes the data following a pattern based anonymization approach wherein data is clustered and for each cluster distinct patterns are identified such that the information loss is minimal.

System and method for risk aware data anonymization

This disclosure relates generally to online learning against data poisoning attack. Conventional methods used data sanitization techniques for online learning against data poisoning attack. However, these methods do not remove poisoned data points from training dataset completely. Embodiments of the present disclosure method provide an influence based defense method for secure online learning against data poisoning attack. The method initially filters a subset of poisoned data points in the training dataset for training a machine learning model using data sanitization technique. Further the method computes an influence of the data points and performs an influence minimization based on a predefined threshold. Updated data points for the learning model are generated and used for training the machine learning model. The disclosed method can be used against data poisoning attacks in applications such as spam filtering, malware detection, recommender system and so on.

Method and system for secure online-learning against data poisoning attack

Data-driven applications depend on training data obtained from multiple internal and external data sources. Hence poisoning of the training data can cause adverse effects in the data driven applications. Conventional methods identifies contaminated test samples and avert them from entering into the training. A generic approach covering all data-driven applications and all types of data poisoning attacks in an efficient manner is challenging. Initially, data aggregation is performed after receiving a ML application for testing. A plurality of feature vectors are extracted from the aggregated data and a poisoned data set is generated. A plurality of personas are generated and are further prioritized to obtain a plurality of attack personas. Further, a plurality of security assessment vectors are computed for each of the plurality of attack personas. A plurality of preventive measures are recommended for each of the plurality of attack personas based on the corresponding security assessment vector.

Method and system for machine learning model testing and preventive measure recommendation

Phishing attacks cause financial frauds and credential thefts. The conventional blacklist, whitelist and Machine Learning (ML) based methods fail to provide an accurate detection of phishing attacks. The present disclosure provides a layered approach wherein a URL domain name is compared with blacklist domains and whitelist domains. Further, the URL undergoes Internet Protocol (IP) address checking followed by context checking. A clicked context is verified based on the number of search results from a popular search engine. Otherwise, the typed context is checked for non-ASCII characters in the domain name. Further, the URL is checked for any brand name. Further, the domain is checked for any misspelling. Further, the URL is examined using a Machine Learning (ML) model. Finally, the URL is classified as phishing if a number hits in a popular search engine is less. Here a phishing alert is generated in each layer based on the corresponding decision.

Method and system for layered detection of phishing websites

Growing community of inventors

Pune, India

Sachin Premsukh Lodha