Search results for "Computer Science"
showing 10 items of 22367 documents
HyperWall: A Hypervisor for Detection and Prevention of Malicious Communication
2020
Malicious programs vary widely in their functionality, from key-logging to disk encryption. However, most malicious programs communicate with their operators, thus revealing themselves to various security tools. The security tools incorporated within an operating system are vulnerable to attacks due to the large attack surface of the operating system kernel and modules. We present a kernel module that demonstrates how kernel-mode access can be used to bypass any security mechanism that is implemented in kernel-mode. External security tools, like firewalls, lack important information about the origin of the intercepted packets, thus their filtering policy is usually insufficient to prevent c…
Deep in the Dark: A Novel Threat Detection System using Darknet Traffic
2019
This paper proposes a threat detection system based on Machine Learning classifiers that are trained using darknet traffic. Traffic destined to Darknet is either malicious or by misconfiguration. Darknet traffic contains traces of several threats such as DDoS attacks, botnets, spoofing, probes and scanning attacks. We analyse darknet traffic by extracting network traffic features from it that help in finding patterns of these advanced threats. We collected the darknet traffic from the network sensors deployed at SURFnet and extracted several network-based features. In this study, we proposed a framework that uses supervised machine learning and a concept drift detector. Our experimental res…
Secure and Privacy Preserving Pattern Matching in Distributed Cloud-based Data Storage
2019
Given two strings: pattern $p$ of length $m$ and text $t$ of length $n$ . The string matching problem is to find all (or some) occurrences of the pattern $p$ in the text $t$ . We introduce a new simple data structure, called index arrays, and design fast privacy-preserving matching algorithm for string matching. The motivation behind introducing index arrays is determined by the need for pattern matching on distributed cloud-based datasets with semi-trusted cloud providers. It is intended to use encrypted index arrays both to improve performance and protect confidentiality and privacy of user data.
The regression Tsetlin machine: a novel approach to interpretable nonlinear regression
2019
Relying simply on bitwise operators, the recently introduced Tsetlin machine (TM) has provided competitive pattern classification accuracy in several benchmarks, including text understanding. In this paper, we introduce the regression Tsetlin machine (RTM), a new class of TMs designed for continuous input and output, targeting nonlinear regression problems. In all brevity, we convert continuous input into a binary representation based on thresholding, and transform the propositional formula formed by the TM into an aggregated continuous output. Our empirical comparison of the RTM with state-of-the-art regression techniques reveals either superior or on par performance on five datasets. Thi…
Automatic Integration of Spatial Data into the Semantic Web
2017
International audience
Self-validating bundles for flexible data access control
2016
Modern cloud-based services offer free or low-cost content sharing with significant advantages for the users but also new issues in privacy and security. To protect sensitive contents (i.e., copyrighted, top secret, and personal data) from the unauthorized access, sophisticated access management systems or/and decryption schemes have been proposed, generally based on trusted applications at client side. These applications work also as access controllers, verifying specific permissions and restrictions accessing user’s resources. We propose secure bundles (S-bundles), which encapsulate a behavioral model (provided as bytecode) to define versatile stand-alone access controllers and encoding/d…
Seismic behavior of structures equipped with variable friction dissipative (VFD) systems
2021
Usually, to mitigate the stresses in framed structures, different strategies are used. Among them, base isolation, viscous/friction/metallic yielding dampers and tuned mass dumpers have been widely investigated. Fluid Viscous Dampers (FVD) probably result the most diffused for the simplicity in the applications. However, these type of dampers request limited interstorey drifts to avoid dangerous effects. Further, they have an elevate cost. On the contrary, friction dampers are not so expensive but request high interstorey drifts to give a significant contribute in the dissipation of energy during an earthquake. In this paper an approach for the energy dissipation by friction, modified with …
On Detection of Network-Based Co-residence Verification Attacks in SDN-Driven Clouds
2017
Modern cloud environments allow users to consume computational and storage resources in the form of virtual machines. Even though machines running on the same cloud server are logically isolated from each other, a malicious customer can create various side channels to obtain sensitive information from co-located machines. In this study, we concentrate on timely detection of intentional co-residence attempts in cloud environments that utilize software-defined networking. SDN enables global visibility of the network state which allows the cloud provider to monitor and extract necessary information from each flow in every virtual network in online mode. We analyze the extracted statistics on d…
BDI Modelling and Simulation of Human Behaviours in Bushfires
2016
Each summer in Australia, bushfires burn many hectares of forest, causing deaths, injuries, and destruction of property. Emergency management strategies rely on expected citizens’ behaviour which differs from reality. In order to raise their awareness about the real population behaviour, we want to provide them with a realistic agent-based simulation. The philosophically-grounded BDI architecture provides a very suitable approach but is little used due to the lack of adapted tools. This paper uses this case study to illustrate two new tools to fill this gap: the Tactics Development Framework (TDF) and GAMA BDI architecture.
Kick Detection and Influx Size Estimation during Offshore Drilling Operations using Deep Learning
2019
An uncontrolled or unobserved influx or kick during drilling has the potential to induce a well blowout, one of the most harmful incidences during drilling both in regards to economic and environmental cost. Since kicks during drilling are serious risks, it is important to improve kick and loss detection performance and capabilities and to develop automatic flux detection methodology. There are clear patterns during a influx incident. However, due to complex processes and sparse instrumentation it is difficult to predict the behaviour of kicks or losses based on sensor data combined with physical models alone. Emerging technologies within Deep Learning are however quite adapt at picking up …