Capturing expertise and enabling efficient information retrieval are critical in the energy sector, where high staff turnover can lead to significant knowledge loss. Retrieval Augmented Generation (RAG) offers a solution by grounding Large Language Model (LLM) outputs in documented sources, but its effectiveness is limited by reliance on general-purpose embeddings. We present Wikatoni, an agentic AI system for energy engineering workflows that integrates a novel domain-specific embedding model. Wikatoni combines fine-tuned embeddings with agentic RAG, metadata filtering, and hybrid retrieval to improve document search, automated reporting, and workflow efficiency. Evaluation on internal enterprise offshore energy data shows that the domain-adapted embedding improves recall by 10%, and Wikatoni agentic RAG further increases answer accuracy by 14% compared to vanilla RAG with the base embedding model, achieving the best overall performance in context recall, faithfulness, and answer accuracy.

Detecting malicious domains is a critical aspect of cybersecurity, with recent advancements leveraging Artificial Intelligence (AI) to enhance accuracy and speed. However, existing browser-based solutions often struggle to achieve both high accuracy and efficient throughput. In this paper, we present MADONNA, a novel browser-based malicious domain detector that exceeds the current state-of-the-art in both accuracy and throughput. MADONNA utilizes feature selection through correlation analysis and model optimization techniques, including pruning and quantization, to significantly enhance detection speed without compromising accuracy. Our approach employs a Shallow Neural Network (SNN) architecture, outperforming Large Language Models (LLMs) and state-of-the-art methods by improving accuracy by 6% (reaching 0.94) and F1-score by 4% (reaching 0.92). We further integrated MADONNA into a Google Chrome extension, demonstrating its practical application with a real-time domain detection accuracy of 94% and an average inference time of 0.87 s. These results highlight MADONNA’s effectiveness in balancing speed and accuracy, providing a scalable, real-world solution for malicious domain detection.

Modern automobiles are equipped with a large number of electronic control units (ECUs) to provide safe, driver assistance and comfortable services. The controller area network (CAN) provides near real-time data transmission between ECUs with adequate reliability for in-vehicle communication. However, the lack of security measures such as authentication and encryption makes the CAN bus vulnerable to cyberattacks, which affect the safety of passengers and the surrounding environment. Detecting attacks on the CAN bus, particularly masquerade attacks, presents significant challenges. It necessitates an intrusion detection system (IDS) that effectively utilizes both CAN ID and payload data to ensure thorough detection and protection against a wide range of attacks, all while operating within the constraints of limited computing resources. This paper introduces an ensemble IDS that combines a gated recurrent unit (GRU) network and a novel autoencoder (AE) model to identify cyberattacks on the CAN bus. AEs are expected to produce higher reconstruction errors for anomalous inputs, making them suitable for anomaly detection. However, vanilla AE models often suffer from overgeneralization, reconstructing anomalies without significant errors, resulting in many false negatives. To address this issue, this paper proposes a novel AE called Latent AE, which incorporates a shallow AE into the latent space. The Latent AE model utilizes Cramér’s statistic-based feature selection technique and a transformed CAN payload data structure to enhance its efficiency. The proposed ensemble IDS enhances attack detection capabilities by leveraging the best capabilities of independent GRU and Latent AE models, while mitigating the weaknesses associated with each individual model. The evaluation of the IDS on two public datasets, encompassing 13 different attacks, including sophisticated masquerade attacks, demonstrates its superiority over baseline models with near real-time detection latency of 25ms.