Acta Cybernetica

EA-POT: An Explainable AI Assisted Blockchain Framework for HoneyPot IP Predictions

Shajulin Benedict — Tue, 22 Nov 2022 00:00:00 +0100

The culpable cybersecurity practices that threaten leading organizations are logically prone to establishing countermeasures, including HoneyPots, and bestow research innovations in various dimensions such as ML-enabled threat predictions. This article proposes an explainable AI-assisted permissioned blockchain framework named EA-POT for predicting potential defaulters' IP addresses. EA-POT registers the predicted defaulters based on the suggestions levied by explainable AI and the approval of IP authorizers to blockchain database to enhance immutability. Experiments were carried out at IoT Cloud Research laboratory using three prediction models such as Random Forest Modeling (RFM), Linear Regression Modeling (LRM), and Support Vector Machines (SVM); and, the observed experimental results for predicting the AWS HoneyPots were explored. The proposed EA-POT framework revealed the procedure to include interpretable knowledge while blacklisting IPs that reach HoneyPots.

Adding Semantics to Measurements: Ontology-Guided, Systematic Performance Analysis

Attila Klenik, András Pataricza — Fri, 02 Sep 2022 00:00:00 +0200

The design and operation of modern software systems exhibit a shift towards virtualization, containerization and service-based orchestration. Performance capacity engineering and resource utilization tuning become priority requirements in such environments.

Measurement-based performance evaluation is the cornerstone of capacity engineering and designing for performance. Moreover, the increasing complexity of systems necessitates rigorous performance analysis approaches. However, empirical performance analysis lacks sophisticated model-based support similar to the functional design of the system.

The paper proposes an ontology-based approach for facilitating and guiding the empirical evaluation throughout its various steps. Hyperledger Fabric (HLF), an open-source blockchain platform by the Linux Foundation, is modelled and evaluated as a pilot example of the approach, using the standard TPC-C performance benchmark workload.

Dual Convolutional Neural Network Classifier with Pyramid Attention Network for Image-Based Kinship Verification

Fri, 02 Jun 2023 00:00:00 +0200

A family is the smallest entity that formed the world with specific characteristics. The characteristics of a family are that the member can/may share some similar DNA and leads to similar physical appearances, including similar facial features. This paper proposed a dual convolutional neural network (CNN) with a pyramid attention network for image-based kinship verification problems. The dual CNN classifier is formed by paralleling the FaceNet CNN architecture followed by family-aware features extraction network and three final fully-connected layers. A channel-wise pyramid attention network is added after the last convolutional layers of FaceNet CNN architecture. The family-aware features extraction network is used to learn family-aware features using the SphereFace loss function. The final features used to classify the kin/non-kin pair are joint aggregation features between the pyramid attention features and family-aware features. At the end of the fully connected layer, a softmax loss layer is attached to learn kinship verification via binary classification problems. To analyze the performance of our proposed classifier, we performed experiments heavily on the Family in The Wild (FIW) kinship verification dataset. The FIW kinship verification dataset is the largest dataset for kinship verification currently available. Experiments of the FIW dataset show that our proposed classifier can achieve the highest average accuracy of 68.05% on a single classifier scenario and 68.73% on an ensemble classifier scenario which is comparable with other state-of-the-art methods.

Refined Fuzzy Profile Matching

Gábor Rácz, Attila Sali, Klaus-Dieter Schewe — Mon, 18 Sep 2023 00:00:00 +0200

A profile describes a set of properties, e.g. a set of skills a person may have or a set of skills required for a particular job. Profile matching aims to determine how well a given profile fits to a requested profile and vice versa. Fuzzyness is naturally attached to this problem. The filter-based matching theory uses filters in lattices to represent profiles, and matching values in the interval [0,1], so the lattice order refers to subsumption between the concepts in a profile. In this article the lattice is extended by additional information in form of weighted extra edges that represent partial quantifiable relationships between these concepts. This gives rise to fuzzy filters, which permit a refinement of profile matching. Another way to introduce fuzzyness is to treat profiles as fuzzy sets. In the present paper we combine these two aproaches. Extra edges may introduce directed cycles in the directed graph of the ontology, and the structure of a lattice is lost. We provide a construction grounded in formal concept analysis to extend the original lattice and remove the cycles such that matching values determined over the extended lattice are exactly those resulting from the use of fuzzy filters in case of crisp profiles. For fuzzy profiles we show how to modify the weighting construction while eliminating the directed cycles but still regaining the matching values. We also give sharp estimates for the growth of the number of vertices in this construction.

Verifying Provable Stability Domains for Discrete-Time Systems Using Ellipsoidal State Enclosures

Andreas Rauh, Auguste Bourgois, Luc Jaulin — Mon, 16 May 2022 00:00:00 +0200

Stability contractors, based on interval analysis, were introduced in recent work as a tool to verify stability domains for nonlinear dynamic systems. These contractors rely on the property that - in case of provable asymptotic stability - a certain domain in a multi-dimensional state space is mapped into its interior after a certain integration time for continuous-time processes or after a certain number of discretization steps in a discrete-time setting. However, a disadvantage of the use of axis-aligned interval boxes in such computations is the omnipresent wrapping effect. As shown in this contribution, the replacement of classical interval representations by ellipsoidal domain enclosures reduces this undesirable effect. It also helps to find suitable ratios for the edge lengths if interval-based domain representations are investigated. Moreover, ellipsoidal domains naturally represent the possible regions of attraction of asymptotically stable equilibrium points that can be analyzed with the help of quadratic Lyapunov functions, for which stability criteria can be cast into linear matrix inequality (LMI) constraints. For that reason, this paper further presents possible interfaces of ellipsoidal enclosure techniques with LMI approaches. This combination aims at the maximization of those domains that can be proven to be stable for a discrete-time range-only localization algorithm in robotics. There, an Extended Kalman Filter (EKF) is applied to a system for which the dynamics are characterized by a discrete-time integrator disturbance model with additive Gaussian noise. In this scenario, the measurement equations correspond to the distances between the object to be localized and beacons with known positions.