Aditya Bakshi

Bio: Aditya Bakshi is an academic researcher from Lovely Professional University. The author has contributed to research in topics: Spoofing attack & Biometrics. The author has an hindex of 3, co-authored 15 publications receiving 16 citations. Previous affiliations of Aditya Bakshi include University of Petroleum and Energy Studies & Shri Mata Vaishno Devi University.

Performance Evaluation of Optimization Techniques with Vector Quantization Used for Image Compression

Abstract: In this paper, performance evaluation has been performed on vector quantization techniques used for image compression. Now a days, vector quantization is a prime area of research and that can be implemented on different algorithms by analyzing the advantages and disadvantages of each algorithms. In this paper, a new technique has been recommended, which will possibly overcome the disadvantage of the Cuckoo Search-LBG algorithm, i.e., CS-LBG is having slower convergence speed as compared to other techniques. So the main goal is to eliminate the disadvantage of CS-LBG. The performance evaluation is done on LBG, PSO-LBG, FA-LBG, HBMO-LBG, QPSO-LBG, BAT-LBG, CS-LBG, and KFCG Algorithm. Further, implementation has been done on hybriding CS-KFCG algorithm and is then compared with CS-LBG, FA-LBG, HBMO-LBG, BAT-LBG, LBG, PSO-LBG algorithms.

An efficient face anti-spoofing and detection model using image quality assessment parameters

Abstract: Biometric authentication poses a significant problem as reconstructed sample or fake self-manufactured samples used by intruders for accessing the actual real legitimate traits. The other prime concern for biometrics is the increasing demand for safety in mobile devices, such as smartphones and tablets etc. So, in the present scenario security for biometrics has gained considerable attention due to various inherent qualities of biometrics. For detection of valid user in a face recognition system with photographs, videos, and 3D models, face liveness detection system is a great technique against spoofing attacks for differentiating between the fake traits from the real traits. In this paper, a novel fake biometric detection technique utilizing liveness detection is proposed for detecting deceitful access attempts in the biometric face system. The prime objective of the paper is to propose a low-complexity fake biometric detection using different image quality assessment parameters i.e. Mean Square Error, Signal to Noise Ratio,SC etc. on the extracted features of the images. The authenticity of the proposed model is confirmed by analyzing the values of MSE, which are 5.8% and 8.49% more than the threshold value of nose and eye features. The same results have also been shown for other 11 different image quality assessment parameters. The experiments were done on the database prepared using the image samples of the 500 male and female students having age between 20 to 30 years.

A Comparative Analysis of Different Intrusion Detection Techniques in Cloud Computing

Abstract: Nowadays, the foremost optimal choice of every IT organization is cloud computing. Cloud computing technology is very flexible and scalable in nature. The prime concern in cloud computing is its security and privacy, because intruders are trying to breach it. The main reason for breaching is its open and distributed architecture. For detection of various attacks on cloud, the most common mechanism used is Intrusion Detection System (IDS). We have presented a comparative analysis of some existing cloud based intrusion detection systems and different methods of deploying the IDS are used for overcoming the security challenges. In spite of the fact that there are various existing literatures in this area of study, we endeavor to give more intricate picture of a thorough analysis. This paper shares an overview of different intrusions in cloud. The metrics, which are used for comparative analysis, are of various types like positioning, detection time, detection techniques, data source and attacks. The comparative analysis also shows the limitations of each technique that tells whether the cloud-computing environment is secure or not.

Lung Cancer Detection Using CT Scan with Artificial Neural Netwok

Abstract: Lung cancer is one of the most common disease in India. Reason behind this disease is unawareness among people and symptoms of disease are only recognized in their posterior stages. In this study, a lung cancer detection technique using Artificial Neural Networks has been investigated. Followed by image enhancement techniques, ANN has been used for classification of lung cancer stages. Lung cancer CT images have been taken from a private hospital. Accuracy of 93.3% has been achieved which is efficient enough as compared to existing systems. In Future, Ant colony optimization can be used with ANN for better results.

Enhanced Image Based Authentication with Secure Key Exchange Mechanism Using ECC in Cloud

Abstract: Cloud computing is the most emerging trend in computing. It provides numerous services like IaaS, PaaS and AaaS. It is a form of pay-per-use based computing. Although it provides tremendous services but there are numerous security issues which need to be resolved. User authentication in cloud computing is the most important step intended towards data security. Image-based authentication is one of the best techniques for user authentication based on the order of selected images. However, key exchange and data encryption in such a complex environment is very difficult to implement. Proposed scheme resolves existing issues of Image based Authentication with Secure key Exchange Mechanism and implements Captcha to detect machine user and Elliptic Curve Cryptography (ECC) for secure key exchange. ECC is the best asymmetric cryptographic algorithm which involves very less key size and computing steps. Hence, it provides a secure layer to cloud computing which deals with user authentication, key exchange and data encryption.

Comprehensive review of hyperspectral image compression algorithms

Abstract: Rapid advancement in the development of hyperspectral image analysis techniques has led to specialized hyperspectral missions. It results in the bulk transmission of hyperspectral images from sensors to analysis centers and finally to data centers. Storage of these large size images is a critical issue that is handled by compression techniques. This survey focuses on different hyperspectral image compression algorithms that have been classified into two broad categories based on eight internal and six external parameters. In addition, we identified research challenges and suggested future scope for each technique. The detailed classification used in this paper can categorize other compression algorithms and may help in selecting research objectives.

A multifaceted framework for adoption of cloud computing in Malaysian SMEs

Abstract: The purpose of this study is to develop a model to understand the relationships among technology, organizational and environmental (TOE) contexts, intention to adopt cloud computing (IACC) and actual usage of cloud computing (AUCC) in small and medium enterprises (SMEs) in Malaysia as a developing country. More specifically, this paper seeks to explore the mediation effect of IACC on the relationship between TOE context and AUCC.,A positivist research approach was selected for this study. Drawing largely upon the TOE framework, this study uses survey data from 209 Malaysian SMEs. Structural equation modelling (SEM) based on partial least squares (PLS) was used to assess the structural relations of the research model.,The results of the structural model show that data security, technology readiness, top management support, competitive pressure and innovativeness are the most significant factors in predicting the adoption of cloud computing in Malaysian SMEs. Further, the results indicate that intention to adopt cloud computing can play a mediating role between TOE factors and the actual usage of cloud computing.,The focus upon Malaysian SMEs may diminish the generalizability of the findings. This study provides profound insight into the management and foundation of cloud computing, different types of cloud services and deployment models that could facilitate the management of enterprise strategic resources and contribute to the performance improvement. This study also provides another important implication for practitioners regarding the absolute necessity of value drivers’ identification within enterprise and understand the causal relationships, which are vital in driving those values.,This study provides several practical guidance for practitioners in deploying cloud services which are most suitable option for their specific technology requirement in their enterprise to enjoy the full benefits of their intangible assets. Another significant implication of this study lies in the fact that it may require a different emphasis on nature and adoption design when there is a higher level of stress on technology-related and cloud computing resources.,This study contributes to the extant literature by developing an integrative model to identify how a wide set of contextual factors can determine the intention to adopt cloud computing and, in turn, influence the actual usage of cloud computing in SMEs in Malaysia as a developing country.

Lung Cancer Detection and Classification from Chest CT Scans Using Machine Learning Techniques

Abstract: Lung cancer is one of the key causes of death amongst humans globally, with a mortality rate of approximately five million cases annually. The mortality rate is even higher than breast cancer and prostate cancer combination. However, early detection and diagnosis can improve the survival rate. Different modalities are used for lung cancer detection and diagnosis, while Computed Tomography (CT) scan images provide the most significant lung infections information. This research’s main contribution is the detection and classification of different kinds of lung cancers such as Adenocarcinoma, Large cell carcinoma, and Squamous cell carcinoma. A novel lung cancer detection technique has been developed using machine learning techniques. The technique comprises feature extraction, fusion using patch base LBP (Local Binary Pattern) and discrete cosine transform (DCT). The machine learning technique such as support vector machine (SVM) and K-nearest neighbors (KNN) evaluated chest CT scan images dataset for texture feature classification. The proposed technique’s performance achieves better accuracy of 93% and 91% for support vector machine and K-nearest neighbors, respectively, than state-of-the-art techniques.

Technique for detection of cooperative black hole attack in MANET

Abstract: Mobile Ad Hoc Network (MANET) is a collection of communication devices or nodes that wish to communicate without any fixed infrastructure and predetermined organization of available links. Security is a major challenge for these networks due to their features of open medium, dynamically changing topologies. The black hole attack is a well known security threat in mobile ad hoc networks. However, it spuriously replies for any route request without having any active route to the specified destination. Sometimes the Black Hole Nodes cooperate with each other with the aim of dropping packets these are known as Cooperative Black Hole attack. This research work suggests the modification of Ad Hoc on Demand Distance Vector Routing Protocol. we are going to use a mechanism for detecting as well as defending against a cooperative black hole attack. This work suggest two new concepts, first one is Maintenance of Routing Information Table and second is Reliability checking of a node. This system also decreases the end to end delay and Routing overhead.

Detection Mechanisms of DDoS Attack in Cloud Computing Environment: A Survey.

Abstract: Distributed Denial of Service (DDoS) attack is considered as one of the major security threats to the cloud computing environment. This attack hampers the adoption and deployment of cloud computing. DDoS Attack is an explicit attempt by an attacker to prevent and deny access to shared services or resources on a server in a cloud environment by legitimate users of cloud computing. This kind of attack targets victim servers by sending massive volumes of traffic from multiple sources to consume all the victim server resources. This paper discussed various defense mechanisms for defending DDoS. The main objective of this paper is to evaluate different mechanisms that help to defend DDoS attacks. This paper highlights the importance of statistical anomaly-based approaches in detecting DDoS attacks.