Biblio
Deep learning has made remarkable achievements in various domains. Active learning, which aims to reduce the budget for training a machine-learning model, is especially useful for the Deep learning tasks with the demand of a large number of labeled samples. Unfortunately, our empirical study finds that many of the active learning heuristics are not effective when applied to Deep learning models in batch settings. To tackle these limitations, we propose a density weighted diversity based query strategy (DWDS), which makes use of the geometry of the samples. Within a limited labeling budget, DWDS enhances model performance by querying labels for the new training samples with the maximum informativeness and representativeness. Furthermore, we propose a beam-search based method to obtain a good approximation to the optimum of such samples. Our experiments show that DWDS outperforms existing algorithms in Deep learning tasks.
Browsers collects information for better user experience by allowing JavaScript's and other extensions. Advertiser and other trackers take advantage on this useful information to tracked users across the web from remote devices on the purpose of individual unique identifications the so-called browser fingerprinting. Our work explores the diversity and stability of browser fingerprint by modifying the rule-based algorithm. Browser fingerprint rely only from the gathered data through browser, it is hard to tell that this piece of information still the same when upgrades and or downgrades are happening to any browsers and software's without user consent, which is stability and diversity are the most important usage of generating browser fingerprint. We implemented device fingerprint to identify consenting visitors in our website and evaluate individual devices attributes by calculating entropy of each selected attributes. In this research, it is noted that we emphasize only on data collected through a web browser by employing twenty (20) attributes to identify promising high value information to track how device information evolve and consistent in a period of time, likewise, we manually selected device information for evaluation where we apply the modified rules. Finally, this research is conducted and focused on the devices having the closest configuration and device information to test how devices differ from each other after several days of using on the basis of individual user configurations, this will prove in our study that every device is unique.
This paper analyzes security problems of modern computer systems caused by vulnerabilities in their operating systems (OSs). Our scrutiny of widely used enterprise OSs focuses on their vulnerabilities by examining the statistical data available on how vulnerabilities in these systems are disclosed and eliminated, and by assessing their criticality. This is done by using statistics from both the National Vulnerabilities Database and the Common Vulnerabilities and Exposures System. The specific technical areas the paper covers are the quantitative assessment of forever-day vulnerabilities, estimation of days-of-grey-risk, the analysis of the vulnerabilities severity and their distributions by attack vector and impact on security properties. In addition, the study aims to explore those vulnerabilities that have been found across a diverse range of OSs. This leads us to analyzing how different intrusion-tolerant architectures deploying the OS diversity impact availability, integrity, and confidentiality.
Current testing for Deep Neural Networks (DNNs) focuses on quantity of test cases but ignores diversity. To the best of our knowledge, DeepXplore is the first white-box framework for Deep Learning testing by triggering differential behaviors between multiple DNNs and increasing neuron coverage to improve diversity. Since it is based on multiple DNNs facing problems that (1) the framework is not friendly to a single DNN, (2) if incorrect predictions made by all DNNs simultaneously, DeepXplore cannot generate test cases. This paper presents Test4Deep, a white-box testing framework based on a single DNN. Test4Deep avoids mistakes of multiple DNNs by inducing inconsistencies between predicted labels of original inputs and that of generated test inputs. Meanwhile, Test4Deep improves neuron coverage to capture more diversity by attempting to activate more inactivated neurons. The proposed method was evaluated on three popular datasets with nine DNNs. Compared to DeepXplore, Test4Deep produced average 4.59% (maximum 10.49%) more test cases that all found errors and faults of DNNs. These test cases got 19.57% more diversity increment and 25.88% increment of neuron coverage. Test4Deep can further be used to improve the accuracy of DNNs by average up to 5.72% (maximum 7.0%).
Smart water networks can provide great benefits to our society in terms of efficiency and sustainability. However, smart capabilities and connectivity also expose these systems to a wide range of cyber attacks, which enable cyber-terrorists and hostile nation states to mount cyber-physical attacks. Cyber-physical attacks against critical infrastructure, such as water treatment and distribution systems, pose a serious threat to public safety and health. Consequently, it is imperative that we improve the resilience of smart water networks. We consider three approaches for improving resilience: redundancy, diversity, and hardening. Even though each one of these "canonical" approaches has been throughly studied in prior work, a unified theory on how to combine them in the most efficient way has not yet been established. In this paper, we address this problem by studying the synergy of these approaches in the context of protecting smart water networks from cyber-physical contamination attacks.
The SDN (Software Defined Networking) paradigm rings flexibility to the network management and is an enabler to offer huge opportunities for network programmability. And, to solve the scalability issue raised by the centralized architecture of SDN, multi-controllers deployment (or distributed controllers system) is envisioned. In this paper, we focus on increasing the diversity of SDN control plane so as to enhance the network security. Our goal is to limit the ability of a malicious controller to compromise its neighboring controllers, and by extension, the rest of the controllers. We investigate a heterogeneous Susceptible-Infectious-Susceptible (SIS) epidemic model to evaluate the security performance and propose a coloring algorithm to increase the diversity based on community detection. And the simulation results demonstrate that our algorithm can reduce infection rate in control plane and our work shows that diversity must be introduced in network design for network security.
Much of the focus of recommender systems research has been on the accurate prediction of users' ratings for unseen items. Recent work has suggested that objectives such as diversity and novelty in recommendations are also important factors in the effectiveness of a recommender system. However, methods that attempt to increase diversity of recommendation lists for all users without considering each user's preference or tolerance for diversity may lead to monotony for some users and to poor recommendations for others. Our goal in this research is to evaluate the hypothesis that users' propensity towards diversity varies greatly and that the diversity of recommendation lists should be consistent with the level of user interest in diverse recommendations. We propose a pre-filtering clustering approach to group users with similar levels of tolerance for diversity. Our contributions are twofold. First, we propose a method for personalizing diversity by performing collaborative filtering independently on different segments of users based on the degree of diversity in their profiles. Secondly, we investigate the accuracy-diversity tradeoffs using the proposed method across different user segments. As part of this evaluation we propose new metrics, adapted from information retrieval, that help us measure the effectiveness of our approach in personalizing diversity. Our experimental evaluation is based on two different datasets: MovieLens movie ratings, and Yelp restaurant reviews.
The vision of cyber-physical systems (CPSs) considered the Internet as the future communication network for such systems. A challenge with this regard is to provide high communication reliability, especially, for CPSs applications in critical infrastructures. Examples include smart grid applications with reliability requirements between 99-99.9999% [2]. Even though the Internet is a cost effective solution for such applications, the reliability of its end-to-end (e2e) paths is inadequate (often less than 99%). In this paper, we propose Reliable Multipath Communication Approach for Internet-based CPSs (RC4CPS). RC4CPS is an e2e approach that utilizes the inherent redundancy of the Internet and multipath (MP) transport protocols concept to improve reliability measured in terms of availability. It provides online monitoring and MP selection in order to fulfill the application specific reliability requirement. In addition, our MP selection considers e2e paths dependency and unavailability prediction to maximize the reliability gains of MP communication. Our results show that RC4CPS dynamic MP selection satisfied the reliability requirement along with selecting e2e paths with low dependency and unavailability probability.
The ever increasing interest in semantic technologies and the availability of several open knowledge sources have fueled recent progress in the field of recommender systems. In this paper we feed recommender systems with features coming from the Linked Open Data (LOD) cloud - a huge amount of machine-readable knowledge encoded as RDF statements - with the aim of improving recommender systems effectiveness. In order to exploit the natural graph-based structure of RDF data, we study the impact of the knowledge coming from the LOD cloud on the overall performance of a graph-based recommendation algorithm. In more detail, we investigate whether the integration of LOD-based features improves the effectiveness of the algorithm and to what extent the choice of different feature selection techniques influences its performance in terms of accuracy and diversity. The experimental evaluation on two state of the art datasets shows a clear correlation between the feature selection technique and the ability of the algorithm to maximize a specific evaluation metric. Moreover, the graph-based algorithm leveraging LOD-based features is able to overcome several state of the art baselines, such as collaborative filtering and matrix factorization, thus confirming the effectiveness of the proposed approach.
Detecting and preventing attacks before they compromise a system can be done using acceptance testing, redundancy based mechanisms, and using external consistency checking such external monitoring and watchdog processes. Diversity-based adjudication, is a step towards an oracle that uses knowable behavior of a healthy system. That approach, under best circumstances, is able to detect even zero-day attacks. In this approach we use functionally equivalent but in some way diverse components and we compare their output vectors and reactions for a given input vector. This paper discusses practical relevance of this approach in the context of recent web-service attacks.