Data Mining - Concepts and Techniques.

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

Due to the proliferation of ICT during the last few decades, there is an exponential increase in the usage of various smart applications such as smart farming, smart healthcare, supply-chain & logistics, business, tourism and hospitality, energy management etc. However, for all the aforementioned applications, security and privacy are major concerns keeping in view of the usage of the open channel, i.e., Internet for data transfer. Although many security solutions and standards have been proposed over the years to enhance the security levels of aforementioned smart applications, but the existing solutions are either based upon the centralized architecture (having single point of failure) or having high computation and communication costs. Moreover, most of the existing security solutions have focussed only on few aspects and fail to address scalability, robustness, data storage, network latency, auditability, immutability, and traceability. To handle the aforementioned issues, blockchain technology can be one of the solutions. Motivated from these facts, in this paper, we present a systematic review of various blockchain-based solutions and their applicability in various Industry 4.0-based applications. Our contributions in this paper are in four fold. Firstly, we explored the current state-of-the-art solutions in the blockchain technology for the smart applications. Then, we illustrated the reference architecture used for the blockchain applicability in various Industry 4.0 applications. Then, merits and demerits of the traditional security solutions are also discussed in comparison to their countermeasures. Finally, we provided a comparison of existing blockchain-based security solutions using various parameters to provide deep insights to the readers about its applicability in various applications.

Blockchain for Industry 4.0: A Comprehensive Review

Software engineering is concerned with the development and evolution of high-quality software systems in a systematic, controlled, and efficient manner. Software engineers are concerned with safety and reliability of the product as well as the cost and schedule of the development process. The lectures and the group projects will cover all aspects of the software life cycle, from development team management, problem specification and analysis, system design techniques, implementation and documentation practices, testing, to maintenance and evaluation of the final product.

Uml Distilled A Brief Guide To The Standard Object Modeling Language

Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text. These results have sparked a renewed interest in the anomaly detection problem and led to the introduction of a great variety of new methods. With the emergence of numerous such methods, including approaches based on generative models, one-class classification, and reconstruction, there is a growing need to bring methods of this field into a systematic and unified perspective. In this review we aim to identify the common underlying principles as well as the assumptions that are often made implicitly by various methods. In particular, we draw connections between classic 'shallow' and novel deep approaches and show how this relation might cross-fertilize or extend both directions. We further provide an empirical assessment of major existing methods that is enriched by the use of recent explainability techniques, and present specific worked-through examples together with practical advice. Finally, we outline critical open challenges and identify specific paths for future research in anomaly detection.

A Unifying Review of Deep and Shallow Anomaly Detection

Anomaly detection is essential towards ensuring system security and reliability. Powered by constantly generated system data, deep learning has been found both effective and flexible to use, with its ability to extract patterns without much domain knowledge. Existing anomaly detection research focuses on a scenario referred to as zero-positive, which means that the detection model is only trained for normal (i.e., negative) data. In a real application scenario, there may be additional manually inspected positive data provided after the system is deployed. We refer to this scenario as lifelong anomaly detection. However, we find that existing approaches are not easy to adopt such new knowledge to improve system performance. In this work, we are the first to explore the lifelong anomaly detection problem, and propose novel approaches to handle corresponding challenges. In particular, we propose a framework called unlearning, which can effectively correct the model when a false negative (or a false positive) is labeled. To this aim, we develop several novel techniques to tackle two challenges referred to as exploding loss and catastrophic forgetting. In addition, we abstract a theoretical framework based on generative models. Under this framework, our unlearning approach can be presented in a generic way to be applied to most zero-positive deep learning-based anomaly detection algorithms to turn them into corresponding lifelong anomaly detection solutions. We evaluate our approach using two state-of-the-art zero-positive deep learning anomaly detection architectures and three real-world tasks. The results show that the proposed approach is able to significantly reduce the number of false positives and false negatives through unlearning.

https://dl.acm.org/doi/pdf/10.1145/3319535.3363226

Lifelong Anomaly Detection Through Unlearning

We explore the task of Android malware detection based on dynamic analysis of application activity sequences using deep learning techniques. We show that analyzing a sequence of the activities is informative for detecting malware, but that analyzing longer sequences does not necessarily lead to a more accurate model. In the real-world scenario, the number of malware is low compared to that of harmless applications. Our dataset has more than 180,000 samples, two-thirds of which are malware. This dataset is significantly larger than other datasets used in previous studies. We mimic real-world cases by randomly sampling a small portion of malware samples. Using the state-of-the-art model BERT, we show that it is possible to achieve desired malware detection performance with an extremely unbalanced dataset. We find that our BERT based model achieves an F1 score of 0.919 with just 0.5% of the examples being malware, which significantly outperforms current state-of-the-art approaches. The results validate the effectiveness of our proposed method in dealing with highly imbalanced datasets.

/pdf/malware-detection-on-highly-imbalanced-data-through-sequence-1g4k4k06z0.pdf

Malware Detection on Highly Imbalanced Data through Sequence Modeling

Bitcoin is a decentralized digital currency that was introduced to the world in 2008. The underlying technology behind bitcoin as well as the other cryptocurrencies which followed it is blockchain technology. Nowadays, collaborative engineering is gaining tremendous popularity, especially in the information technology industry. In the future, technological giants may have to work with each other to complete large projects of great importance and significance. In such projects, trust management is crucial. With multiple parties involved in such projects, it is important that no party monopolizes the project and adds patches which are not known to the other parties. In addition, no party should have the authority to disclose the full contents of the work to a third party. In this paper, we propose a blockchain based solution to the above issues. The only authentic version of the project would be the one maintained in the blockchain. Collaborators would broadcast the changes they make, and it would be added to the blockchain only after consensus from all parties. We use a threshold key system on private keys so that consensus is achieved. Our proposed system guarantees secure release of the project as well as non-repudiation to collaborators.

Smart Collaboration Mechanism Using Blockchain Technology

With technological advancements and the increasing use of computers and internet in our day to day lives, the issue of security has become paramount. The rate of cybercrime has increased tremendously in the internet era. Out of the numerous crimes, identity theft is perhaps the one that poses the most dangers to an individual. More and more voices strongly declare that the password is no longer a reliable IT security measure and must be replaced by more efficient systems for protecting the computer contents. Behavioural biometrics is an emerging technology that resolves some of the major flaws of the previous scheme. This paper is the first stage of a project which aims to develop a novel authentication system using behavioural biometrics. It presents a comprehensive survey of various techniques and recent works in the respective fields.

A Literature Survey on Authentication Using Behavioural Biometric Techniques

With the advent of the Internet, social media platforms have become an increasingly popular medium of communication for people. Platforms like Twitter and Quora allow people to express their opinions on a large scale. These platforms are, however, plagued by the problem of hate speech and toxic content. Such content is generally sexist, homophobic or racist. Automatic text classification can filter out toxic content so some extent. In this paper, we discuss the adversarial attacks on hate speech classifiers. We demonstrate that by changing the text slightly, a classifier can be fooled to misclassifying a toxic comment as acceptable. We attack hate speech classifiers with known attacks as well as introduce four new attacks. We find that our method can degrade the performance of a Random Forest classifier by 20%. We hope that our work sheds light on the vulnerabilities of text classifiers, and opens doors for further research on this topic.

Rajvardhan Oak

Papers

Lifelong Anomaly Detection Through Unlearning

Malware Detection on Highly Imbalanced Data through Sequence Modeling

Smart Collaboration Mechanism Using Blockchain Technology

A Literature Survey on Authentication Using Behavioural Biometric Techniques

Poster: Adversarial Examples for Hate Speech Classifiers