Abstract Manual penetration testing is increasingly inadequate against rapidly evolving cyber threats, as it is time-consuming, difficult to scale, and heavily reliant on human expertise. Whilst Artificial Intelligence (AI), particularly Large Language Models (LLMs), offers automation potential, current tools suffer from poor reasoning, limited context retention, low scalability, and safety and misuse concerns. This paper introduces AutoSecAgent, an AI-powered platform designed to address these limitations. Built on the adaptive Agent Zero orchestration framework and powered by the cybersecurity-focused DeepSeek LLM, AutoSecAgent supports semi-automated end-to-end penetration testing under human oversight, covering vulnerability discovery, exploitation, and reporting with remediation guidance for follow-up. It features recursive memory embedding to maintain context across complex multi-step attack chains, supporting strategic planning and situational awareness. Additionally, real-time Retrieval-Augmented Generation (RAG) allows AutoSecAgent to source up-to-date vulnerability data from repositories such as NVD and CVE, ensuring attack strategies incorporate current information. Its modular, agent-based architecture supports scalability across diverse network environments and integrates with tools such as Metasploit and Nmap. To avoid scattered claims across multiple design elements, this study focuses its core contributions on two tightly coupled points: (i) a memory-centric orchestration mechanism (Recursive Memory Embedding, RME) with an explicit operationalisation of context-loss errors for penetration testing trajectories and (ii) a reproducible, tool-grounded, semi-automated workflow that combines RME with real-time retrieval and a bounded online optimisation loop under human oversight. Multi-agent decomposition and DeepSeek domain tuning are treated as supporting design choices that enable these two contributions rather than separate innovations. Experimental results indicate that this design improves end-to-end performance over representative LLM-based baselines across vulnerability detection, exploitation, multi-step attack completion, and scalability in controlled evaluation settings. The empirical study is positioned as a proof-of-concept validation in controlled and semi-realistic settings. Broader operational generalisation and comparison against additional non-LLM baseline classes (e.g. scanner-only pipelines) are treated as future work.

Magnetic Resonance Imaging (MRI) reconstruction faces many challenges due to limited access to diverse training data, primarily driven by privacy concerns. This is where Federated Learning (FL) comes as a solution, enabling collaborative model training between several clients without direct data sharing. However, the varied data quality and computational capabilities of participating clients can significantly impact FL’s efficiency and performance in MRI reconstruction. In this paper, we introduce an adaptive client selection strategy for federated MRI reconstruction. Our method dynamically assesses client contributions, considering factors like data quality, diversity, and computational resources. This allows us to prioritize clients that offer the most beneficial updates to the global model. Through extensive experiments on various MRI datasets, we demonstrate that our adaptive approach significantly improves reconstruction quality and accelerates convergence compared to traditional FL. Moreover, our method consistently outperforms both random client selection and training with all available clients.

Deepfake technology presents critical cybersecurity challenges that have become more popular since easily accessible applications have become more widely available. The proliferation of fake portrait videos constitutes a serious risk to the legal system, society, and personal privacy. The publication of fraudulent explicit content starring celebrities, the circulation of fake political videos, and the use of faked impersonated videos as proof in court of law are all examples of the effects of deepfakes in the real world. In reaction to this growing threat, we propose a simple yet efficient Person of Interest (PoI) Siamese network-based model to detect deepfake synthetic content in portrait images, providing a preventative measure against the growing danger of deepfakes. On one side and unlike traditional neural networks, which process inputs independently, our approach leverages a Siamese network that processes two inputs simultaneously using identical sub-networks with shared weights and parameters. This twin structure is particularly effective for our adopted PoI methodology, where one input is a reference image of a specific individual, and the other is an image that needs to be verified as either real or fake. By ensuring that both the reference and the suspect image are processed in the same way, the network can accurately learn and detect subtle differences, enabling it to determine whether the second image is a genuine representation of the individual or a deepfake. This makes our method particularly relevant for targeted forensic investigations or security applications where an individual’s media integrity is paramount. On the other side, our proposed method does not require any additional complex biological feature extraction. Despite this simplification, our method achieves comparable accuracy to more complex models that rely on biological feature extraction. This efficiency makes our approach practical for implementation on resource-constrained devices, such as mobile phones and Internet of Things (IoT) systems.

Light field technology represents a viable path for providing a high-quality VR content. However, such an imaging system generates a high amount of data leading to an urgent need for LF image compression solution. In this paper, we propose an efficient LF image coding scheme based on view synthesis. Instead of transmitting all the LF views, only some of them are coded and transmitted, while the remaining views are dropped. The transmitted views are coded using Versatile Video Coding (VVC) and used as reference views to synthesize the missing views at decoder side. The dropped views are generated using the efficient dual discriminator GAN model. The selection of reference/dropped views is performed using a rate distortion optimization based on the VVC temporal scalability. Experimental results show that the proposed method provides high coding performance and overcomes the state-of-the-art LF image compression solutions.

The increasing penetration of acquisition and display devices for Light Field (LF) content in the consumer market leads to the high proliferation of this new immersive media. This growing interest to LF images thus urgently raises the question of their compression. In this paper, we propose a convolutional neural networks (CNN)-based LF image coding scheme including both Rate Distortion Optimization (RDO) and post-processing steps. First, at the encoder side, the views are rearranged in sparse and dropped set of views. The former are compressed with a standard encoder and transmitted, while the dropped views are either linearly approximated or synthesized by a CNN using the encoded views as input. This choice is made on the basis of the proposed RDO process. At the decoder side, once the dropped views are either linearly approximated or synthesized by a CNN block, a post-processing step is performed to further enhance the quality of the reconstructed views. This post-processing block is based on superpixel to pixel-matching. Experimental results show that the proposed scheme provides views with high visual quality and overcomes the state-of-the-art LF image compression solutions by -30% in terms of BD-BR and 0.62 dB in BD-PSNR.

Computer vision applications such as refocusing, segmentation and classification become one of the most advanced imaging services. Light Field (LF) imaging systems provide a rich semantic information of the scene. Using a dense set of cameras and microlens arrays (Plenoptic camera), the direction of each ray coming from the scene toward the LF capture system can be extracted and represented by spatial and angular coordinates. However, such imaging system induces many drawbacks including the large amount of data produced and complexity increase for scene representation. In this paper, we propose an efficient LF image coding scheme. This scheme first encodes a sparse set of views using the latest hybrid video encoder (JEM). Then, it estimates a second sparse set of views using a linear approximation. At the decoder side, we use a Deep Learning (DL) approach to estimate the whole LF image from the reconstructed sparse sets of views. Experimental results show that the proposed scheme provides higher visual quality and overcomes the state of the art LF image compression solution by 30 % bitrate gain.

This paper presents a new scalable locally adaptive resolution lossless low-complexity (LAR-LLC) image codec. It is based on the LAR framework that is a multiresolution compression method supporting both lossy and lossless coding. To achieve an efficient low-complexity solution, each processing stage of the LAR is modified. For the first step, consisting of a pyramidal decomposition, a new reversible transform called hierarchical diagonal$S$transform (HD-ST) is proposed. The HD-ST operates on sets of data pairs, requiring only shift and add/sub operations. The second step performs the prediction of the transformed coefficients. The prediction scheme considers both inter- and intra-level information, and involves fixed weights. Then, a classification process is introduced to separate prediction errors into subclasses, using a context modeling approach. Finally, each subclass is coded by the Huffman coding algorithm. The results of the lossless compression experiments showed that LAR-LLC achieves the same compression performance as JPEG2000 with a lower complexity.

Along with the digital evolution, image post-production and indexing have become one of the most advanced and desired services in the lossless 3D image domain. The 3D context provides a significant gain in terms of semantics for scene representation. However, it also induces many drawbacks including monitoring visual degradation of compressed 3D image (especially upon edges), and increased complexity for scene representation. In this paper, we propose a semantic region representation and a scalable coding scheme. First, the semantic region representation scheme is based on a low resolution version of the 3D image. It provides the possibility to segment the image according to a desirable balance between 2D and depth. Second, the scalable coding scheme consists in selecting a number of regions as a Region of Interest (RoI), based on the region representation, in order to be refined at a higher bitrate. Experiments show that the proposed scheme provides a high coherence between texture, depth and regions and ensures an efficient solution to the problems of compression and scene representation in the 3D image domain.