In this paper, we propose a novel approach that enables simultaneous localization, mapping (SLAM) and objects recognition using visual sensors data in open environments that is capable to work on sparse data point clouds. In the proposed algorithm the ORB-SLAM uses the current and previous monocular visual sensors video frame to determine observer position and to determine a cloud of points that represent objects in the environment, while the deep neural network uses the current frame to detect and recognize objects (OR). In the next step, the sparse point cloud returned from the SLAM algorithm is compared with the area recognized by the OR network. Because each point from the 3D map has its counterpart in the current frame, therefore the filtration of points matching the area recognized by the OR algorithm is performed. The clustering algorithm determines areas in which points are densely distributed in order to detect spatial positions of objects detected by OR. Then by using principal component analysis (PCA)—based heuristic we estimate bounding boxes of detected objects. The image processing pipeline that uses sparse point clouds generated by SLAM in order to determine positions of objects recognized by deep neural network and mentioned PCA heuristic are main novelties of our solution. In contrary to state-of-the-art approaches, our algorithm does not require any additional calculations like generation of dense point clouds for objects positioning, which highly simplifies the task. We have evaluated our research on large benchmark dataset using various state-of-the-art OR architectures (YOLO, MobileNet, RetinaNet) and clustering algorithms (DBSCAN and OPTICS) obtaining promising results. Both our source codes and evaluation data sets are available for download, so our results can be easily reproduced.

Ensuring software quality during development requires effective regression testing. However, test suites in open-source libraries often grow large, redundant, and difficult to maintain. Most traditional test suite optimization methods treat test cases as atomic units, without analyzing the utility of individual instructions. This paper presents an intelligent method for test case synthesis using a Q-learning agent. The agent learns to construct compact test cases by interacting with an execution environment and receives rewards based on branch coverage improvements and simultaneous reductions in test case length. The training process includes a pretraining phase that transfers knowledge from the original test suite, followed by adaptive learning episodes on individual test cases. As a result, the method requires no formal documentation or API specifications and uses only execution traces of the original test cases. An explicit synthesis algorithm constructs new test cases by selecting API calls from a learned policy encoded in a Q-table. Experiments were conducted on two open-source C++ libraries of differing API complexity and original test suite size. The results show that the proposed method can reach up to 67% test suite reduction while preserving branch coverage, confirming its effectiveness for regression test suite minimization in resource-constrained or specification-limited environments.

The rapid integration of Unmanned Aerial Vehicles (UAVs) into smart city infrastructures necessitates advanced security measures to ensure their safe and sustainable operation. However, existing Automatic Dependent Surveillance–Broadcast (ADS-B) systems are highly vulnerable to spoofing, data falsification, and cyber threats, which compromises air traffic management and poses significant challenges to UAV security. This paper presents an innovative approach to improving UAV security by introducing a novel steganographic method for ADS-B data protection. The proposed method leverages Fourier transformation to embed UAV identifiers into ADS-B signals, ensuring a high level of concealment and robustness against signal distortions. A key feature of the approach is the dynamic parameter management system, which adapts to varying transmission conditions to minimize distortions and enhance resilience. Experimental validation demonstrates that the method achieves a tenfold reduction in Mean Squared Error (MSE) and Normalized Mean Squared Error (NMSE) compared to existing techniques such as mp3stego while also improving the Signal-to-Noise Ratio (SNR) and Peak Signal-to-Noise Ratio (PSNR) compared to s-tools. The proposed solution ensures compliance with existing ADS-B standards, maintaining seamless integration with air traffic management systems while enhancing cybersecurity measures. By safeguarding UAV communications, the method contributes to the sustainable development of smart cities and supports critical applications such as logistics, environmental monitoring, and emergency response operations. These findings confirm the practical feasibility of the proposed approach and its potential to strengthen UAV security and ADS-B data protection, ultimately contributing to the resilience and sustainability of urban airspace infrastructure.

Deep learning-based feature extraction methods and transfer learning have become common approaches in the field of pattern recognition. Deep convolutional neural networks trained using tripled-based loss functions allow for the generation of face embeddings, which can be directly applied to face verification and clustering. Knowledge about the ground truth of face identities might improve the effectiveness of the final classification algorithm; however, it is also possible to use ground truth clusters previously discovered using an unsupervised approach. The aim of this paper is to evaluate the potential improvement of classification results of state-of-the-art supervised classification methods trained with and without ground truth knowledge. In this study, we use two sufficiently large data sets containing more than 200,000 “taken in the wild” images, each with various resolutions, visual quality, and face poses which, in our opinion, guarantee the statistical significance of the results. We examine several clustering and supervised pattern recognition algorithms and find that knowledge about the ground truth has a very small influence on the Fowlkes–Mallows score (FMS) of the classification algorithm. In the case of the classification algorithm that obtained the highest accuracy in our experiment, the FMS improved by only 5.3% (from 0.749 to 0.791) in the first data set and by 6.6% (from 0.652 to 0.718) in the second data set. Our results show that, beside highly secure systems in which face verification is a key component, face identities discovered by unsupervised approaches can be safely used for training supervised classifiers. We also found that the Silhouette Coefficient (SC) of unsupervised clustering is positively correlated with the Adjusted Rand Index, V-measure score, and Fowlkes–Mallows score and, so, we can use the SC as an indicator of clustering performance when the ground truth of face identities is not known. All of these conclusions are important findings for large-scale face verification problems. The reason for this is the fact that skipping the verification of people’s identities before supervised training saves a lot of time and resources.

In this paper, we present an agent-based model of a controlled detonation system for dynamic sandbox analysis of suspicious software. Instead of treating the sandbox as a passive observer, the model places an AI operator inside the analysis loop and allows it to perform adaptive GUI interactions in a plausible, isolated execution environment. The controlled detonation process is formulated as a partially observable Markov decision process (POMDP), while the proposed proof-of-concept architecture combines initial profiling, VM preparation, multi-layer telemetry, and an RL policy with visual perception and temporal memory. Evaluation in a controlled emulation setting on 180 malware samples from three threat classes shows higher Activity Rates and Coverage, and shorter Time-to-Reveal than passive and fixed scripted baselines. These results support the feasibility of adaptive interactions as a promising direction for sandbox analysis, while broader external validation, matched comparisons with prior systems, and component-wise ablation remain future work.