Search

Nowadays, Phishing attack has gained more attention among all the other attacks existing in online social media. The fraudulent E-mail sent form the fake website that looks like the legitimate website is the initial carter for launching the phishing attacks. This is a kind of social engineering attack in which, the user is targeted for stealing the personal information, viz., user name, password, and banking credentials for committing the financial crimes. The existing phishing website detection methods suffer from two issues in terms of feature selection scheme that does not consider the right set of features for detection and the classifier which is trained with the poor hyper parameters. In this paper, the phishing websites are detected by extracting the various features from the collection of phishing and legitimate websites obtained from PhishTank and starting point directory service. This constructed feature vector is further processed by the proposed feature selection module GenFea to obtain the reduced set of features. This reduced feature vector is further processed by the proposed phishing detection module PhiDec to predict the type of a website. The performance of the proposed approach is compared with the existing machine learning classifiers and neural network classifiers. From the experimental results, it is observed that the proposed approach outperformed the other existing classifiers for detecting the phishing websites.

Denial of Service (DoS) attack has been considered as one of the most promising threats to network security that denies access to services offered by networks or servers for legitimate users. Therefore, to protect the computing resources against these attacks, DoS attack detection system is needed. The existing statistical based attack detection systems face the lacuna of crippling dimensionality and suffer from low accuracy and high false alarm. In this paper, to address this issue, a system for the detection of DoS attacks using Feature Correlation Map (FCM) based statistical approach is proposed. FCM is the process of extracting the correlative information between selected features of each record. The normal traffic profile is constructed using Hellinger Distance measure. The distance between FCM and mean of normal traffic FCMs is computed to determine if the new network traffic belongs to either normal or attack traffic. The proposed approach is tested with benchmark datasets and compared with state-of-the-art statistical attack detection systems. It is evident that the proposed approach yields promising results than the existing attack detection systems.

Nowadays Denial of Service (DoS) attack is one of the threatening cyber attacks for the users of Internet which denies online services for legitimate users. Therefore, DoS attack detection mechanism is needed to protect the online services from these attacks. A number of machine learning based attack detection mechanisms exist and the existing detection mechanisms face the lacuna of identifying known and unknown DoS attacks and suffer from low accuracy and high false alarm. In this paper, these issues are addressed by proposing a Vector Convolutional Deep Feature Learning (VCDeepFL) approach for identification of DoS attacks. The VCDeepFL approach is a combination of Vector Convolutional Neural Network (VCNN) and Fully Connected Neural Network (FCNN). VCNN extracts the feature by down sampling the input vector and provides a better representation of input vector. FCNN is a multiclass classifier that boosts the performance of the attack detection system by automatically computing the best set of weights from training. The proposed approach is tested with NSL KDD dataset and compared with state of the art attack detection system and base classifiers. It is evident that the proposed approach yields prominent results for most of the classes. Further, Receiver Operating Characteristics (ROC) analysis is performed and it is seen from the ROC curve that the Area Under the Curve (AUC) is high for the proposed approach.

A kinetic spectrophotometric method is described for the detection and determination of propellant grade hydrazines and its derivatives based on their reaction with 1-chloro-2,4-dinitrobenzene (CDNB) incorporated in a solution matrix of polyaniline-Emaraldine Base (Pani-EB) to produce HCl. This strong acid protonates (dopes) Pani (EB-Blue) to form Pani Emeraldine salt (ES-Green). A kinetic study based on the gradual decrease in absorbance at 626 nm for both nano and conventional Pani–CDNB systems was carried out at 50 °C and 60 °C under optimized conditions in the dynamic concentration range of 0.1–0.004 M. Initial rate and fixed time methods were adopted for constructing calibration curves. Hydrazines were determined based on the linear relationship between percent absorbance change at 30 min. and their concentration. R.S.D. for five replicate determinations of each one of these hydrazines using both systems is less than 1.5%. Minimum detectable limits for hydrazines were found for both systems. This method was successfully applied for determination of hydrazines in tap water with satisfactory analytical results.

Denial of Service (DoS) attacks represent a major threat to network security, especially in today's networked world. There has been significant research in this area, primarily focused on mitigating and preventing DoS attacks affecting transport layer services. This paper addresses issues arising from a new variation of a DoS attack, namely the SlowPOST attack that affects Application Layer services. In SlowPOST, the malicious clients send data at a slow rate after the connection is established, and the server is left waiting for the data to arrive. These attacks are particularly devastating due to their ability to resist detection due to their protocol compliance. In addition, such attacks do not require the massive resources that DoS attacks normally require, making them easier to launch. Some solutions for this issue have already been deployed in some commercial servers. These solutions are based on either monitoring traffic or enforcing a time limit on the transmission of the protocol headers. In order to achieve reliable detection, the detection parameters need to adapt to the constantly changing traffic. This paper proposes a novel algorithm that uses the data rate of connections to evolve a threshold for determining potential attackers in SlowPOST. This proposed method is tested by subjecting a server to an attack, and it was observed that in the absence of this method, the servicing of legitimate requests is not completed.

An Application Layer Distributed Denial of Service Attack (DDoS) is one of the biggest concerns for web security. Many detection methods are designed to mitigate DDoS attack based on IP and TCP layer instead of the Application layer. These methods are not suitable for detection of Application layer DDoS attack since most of the IP and TCP layer DDoS attacks are based on request flooding attack. But Application layer DDoS attacks consist of request flooding, session flooding, and asymmetric attack. The solutions available to detect Application layer DDoS attack, detect only limited number of Application layer DDoS attacks. The solutions that detect all types of Application layer DDoS attacks have huge algorithm complexity. One of the major challenges in the detection of an Application layer DDoS attack is the non-availability of features to detect such attacks. Hence it is difficult to model normal user behavior from attack behavior. In this paper, Deep learning architecture is introduced to learn deep features of Application layer DDoS attack. Deep learning architecture consist of very deep neural network, typically more than three layers. In the proposed work the concept of AutoEncoder is applied, which is one of the deep learning based models that learns deep useful features in the Application layer DDoS attack dataset. The Stacked AutoEncoder deep learning architecture, is aimed to receive high level features. The performance of the proposed method was evaluated in terms of the metrics such as false positive rate and detection rate. Comparison of the proposed method with the existing methods reveals that the proposed method performs better than the existing methods.

The current Android application framework has an "all or none" permission policy, viz., an application can be installed if and only if all the permissions are granted. Also, no provision exists to deny granted permissions after installation. Therefore, any application can misuse the granted permission. CyanogenMod addresses this issue by denying the unwanted permissions which might cause the application to crash. WhisperCore, has worked on this problem but the working model is unavailable at the moment. APEX, also is currently doing some research on this issue but there is no publicly available document. In this paper, the problem of misusing the granted permission n in Android is addressed and a novel idea of 'shadow manifest' is proposed. The proposed shadow manifest is implemented by creating a novel Content Provider, viz., SelPermProvider, which hosts the user permissions. In general, during the resource request phase, the system manifest is checked and the resources are allocated. But, in our implementation, the control is altered to flow through the shadow manifest after the system manifest is checked. If the query to shadow manifest is TRUE, then the resource is granted else a dummy or null value is returned. This facilitates the user to identify the malware and block the malware from achieving the intended task. Thus, the application is unaware of the indirect permission denial and continues to run normally. The user can decide which permission to restrict by checking a log of all recent permission requests, a facility provided in our app. The proposed shadow manifest has been implemented and tested using an application called 'Contacts_Retrieve'. It was found to successfully complete the application if the shadow manifest returned TRUE, and unsuccessfully complete otherwise.

Problem statement: This study proposes a new idea for generation of minimized test suite in the test case generation using the mutant gene algorithm, which not only identifies the best test cases but also reduces the number of test cases generated, selects test cases optimally there improving the performance in testing of software. Test cases are generated by using branch coverage algorithm and a coverage table is created for verifying branch coverage. Approach: The process of minimization was done through Mutant gene algorithm. Mutant gene algorithm combined both the mutation testing process and genetic algorithm. Initially a number of chromosomes were generated in random order. Mutation score was used for finding fitness function. The fitness function was found for all the randomly generated chromosomes by applying the mutant score to the function. Rank based selection was used for selecting the chromosomes. After the selection of the chromosomes one-point crossover was performed. A population of chromosomes obtained, which was given as the input for the next iteration. Large iterations were performed to obtain the best test case with higher fitness value, it was the end condition. Results: Between the measured iterations the value of the mutant score remained constant. The results of the experiments showed that the minimization process was competitive with other methods and even outperforms them for complex cases. Conclusion: The whole generation and minimization process was fully automated; redundant explorations of test case were avoided, resulting in efficient generation of test cases.

A simple, highly selective and rapid gas chromatography method (packed column with flame ionization detection) has been developed to determine hydrazine and monomethylhydrazine individually and for selective determination of hydrazine in the UH 25 mixture in organic medium. This method is based on the derivatization of hydrazine (at ambient temperature) with 1,1,1-trifluoro-4-(3-thienyl) (CF3 enone) in the absence of catalyst/buffer which leads to the formation of corresponding pyrazolidine/pyrazoline/pyrazole. The organic derivatives thus formed are then detected and their presence is confirmed by GC-MS. The GC method provides good resolution between CF3 enone and its derivatives with a total analysis time of 20 min. The concentration of CF3 enone and derivatization time are optimized to determine hydrazines in the concentration range of 0.4 mM to 0.2 M. The calibration curves based on peak areas of CF3 enone and its derivatives showed good linearity with r(2) ≈ 0.999 for the working range and the precision was found to be less than 1% for hydrazine, MMH and hydrazine in UH25. The recovery was found by the standard addition method. Under the established conditions, limits of detection were 20 μM for hydrazine, 10 μM for MMH and 20 μM for hydrazine in UH25. The tolerance limit for interfering amines was also found. The advantage of this method is the selective detection and determination of hydrazine in the UH25 mixture as 1,1-dimethylhydrazine present in UH25 cannot be derivatized with CF3 enone.