Surveillance systems regularly create massive video data in the modern technological era, making their analysis challenging for security specialists. Finding anomalous activities manually in these enormous video recordings is a tedious task, as they infrequently occur in the real world. We proposed a minimal complex deep learning-based model named EADN for anomaly detection that can operate in a surveillance system. At the model’s input, the video is segmented into salient shots using a shot boundary detection algorithm. Next, the selected sequence of frames is given to a Convolutional Neural Network (CNN) that consists of time-distributed 2D layers for extracting salient spatiotemporal features. The extracted features are enriched with valuable information that is very helpful in capturing abnormal events. Lastly, Long Short-Term Memory (LSTM) cells are employed to learn spatiotemporal features from a sequence of frames per sample of each abnormal event for anomaly detection. Comprehensive experiments are performed on benchmark datasets. Additionally, the quantitative results are compared with state-of-the-art methods, and a substantial improvement is achieved, showing our model’s effectiveness.

This study proposes a novel approach leveraging Large Language Models (LLMs) to generate dynamic and complex adaptable cybersecurity exercise scenarios. Motivated by Turing’s seminal exploration into machine cognition, which questions the ability of machines to mimic human thought and intelligence. By exploiting the generative potential of LLMs, our methodology simulates a wide range of cyber threats, both known and novel, thereby enhancing cybersecurity training and awareness. This approach transforms the potential for ’hallucination’ inherent in LLMs into a potential advantage, enabling the creation of complex exercise scenarios that push the boundaries of traditional cybersecurity training. The innovation lies in the sophisticated application of AI, aiming to advance the preparedness of security professionals against diverse cyber threats. The scenarios generated through this method were subject to meticulous testing and a rigorous evaluation process involving (Generated Pre-Trained Transformer) GPT models and expert review to ensure their realism and applicability. In this paper, we introduce ’CyExec,’ a novel approach leveraging GPT to dynamically generate cybersecurity training scenarios. Furthermore, the prompts provided to the LLMs were meticulously designed to adopt a Retrieval-Augmented Generation (RAG) approach, enriching the complexity and relevance of the scenarios. This incorporation of RAG, alongside the inspiration drawn from Turing’s exploration of machine intelligence, showcases an advanced application of AI in cybersecurity training, reflecting a deep understanding of how machines can augment our capabilities to anticipate and mitigate cyber threats.

Facial emotion recognition is a crucial task for human-computer interaction, autonomous vehicles, and a multitude of multimedia applications. In this paper, we propose a modular framework for human facial emotions’ recognition. The framework consists of two machine learning algorithms (for detection and classification) that could be trained offline for real-time applications. Initially, we detect faces in the images by exploring the AdaBoost cascade classifiers. We then extract neighborhood difference features (NDF), which represent the features of a face based on localized appearance information. The NDF models different patterns based on the relationships between neighboring regions themselves instead of considering only intensity information. The study is focused on the seven most important facial expressions that are extensively used in day-to-day life. However, due to the modular design of the framework, it can be extended to classify N number of facial expressions. For facial expression classification, we train a random forest classifier with a latent emotional state that takes care of the mis-/false detection. Additionally, the proposed method is independent of gender and facial skin color for emotion recognition. Moreover, due to the intrinsic design of NDF, the proposed method is illumination and orientation invariant. We evaluate our method on different benchmark datasets and compare it with five reference methods. In terms of accuracy, the proposed method gives 13% and 24% better results than the reference methods on the static facial expressions in the wild (SFEW) and real-world affective faces (RAF) datasets, respectively.

Deep Learning-based chest Computed Tomography (CT) analysis has been proven to be effective and efficient for COVID-19 diagnosis. Existing deep learning approaches heavily rely on large labeled data sets, which are difficult to acquire in this pandemic situation. Therefore, weakly-supervised approaches are in demand. In this paper, we propose an end-to-end weakly-supervised COVID-19 detection approach, ResNext+, that only requires volume level data labels and can provide slice level prediction. The proposed approach incorporates a lung segmentation mask as well as spatial and channel attention to extract spatial features. Besides, Long Short Term Memory (LSTM) is utilized to acquire the axial dependency of the slices. Moreover, a slice attention module is applied before the final fully connected layer to generate the slice level prediction without additional supervision. An ablation study is conducted to show the efficiency of the attention blocks and the segmentation mask block. Experimental results, obtained from publicly available datasets, show a precision of 81.9% and F1 score of 81.4%. The closest state-of-the-art gives 76.7% precision and 78.8% F1 score. The 5% improvement in precision and 3% in the F1 score demonstrate the effectiveness of the proposed method. It is worth noticing that, applying image enhancement approaches do not improve the performance of the proposed method, sometimes even harm the scores, although the enhanced images have better perceptual quality.

The rise of social media has enabled individuals with biased perspectives to spread hate speech, directing it toward individuals based on characteristics such as race, gender, religion, or sexual orientation. Constructive interactions in varied communities can greatly enhance self-esteem, yet it is vital to consider that adverse comments may affect individuals’ social standing and emotional health. The crucial task of detecting and addressing this type of content is imperative for reducing its negative effects on communities and individuals alike. The rising occurrence highlights the urgency for enhanced methods and robust regulations on digital platforms to protect humans from such prejudicial and damaging conduct. Hate speech typically appears as a deliberate hostile action aimed at a particular group, often with the intent to demean or isolate them based on various facets of their identity. Research on hate speech predominantly targets resource-aware languages like English, German, and Chinese. Conversely, resource-limited languages, including European languages such as Italian, Spanish, and Portuguese, alongside Asian languages like Roman Urdu, Korean, and Indonesian, present obstacles. These challenges arise from a lack of linguistic resources, making the extraction of information a more strenuous task. This study is focused on the detection and improvement of multilingual hate speech detection across 13 different languages. To conduct a thorough analysis, we carried out a series of experiments that ranged from classical machine learning techniques and mainstream deep learning approaches to recent transformer-based methods. Through hyperparameter tuning, optimization techniques, and generative configurations, we achieved robust and generalized performance capable of effectively identifying hate speech across various dialects. Specifically, we achieved a notable enhancement in detection performance, with precision and recall metrics exceeding baseline models by up to 10% across several lesser-studied languages. Additionally, our work extends the capabilities of explainable AI within this context, offering deeper insights into model decisions, which is crucial for regulatory and ethical considerations in AI deployment. Our study presents substantial performance improvements across various datasets and languages through meticulous comparisons. For example, our model significantly outperformed existing benchmarks: it achieved F1-scores of 0.90 in German (GermEval-2018), up from the baseline score of 0.72, and 0.93 in German (GermEval-2021), a substantial increase from 0.58. Additionally, it scored 0.95 in Roman Urdu HS, surpassing the previous peak of 0.91. Furthermore, for mixed-language datasets such as Italian and English (AMI 2018), our accuracy rose dramatically from 0.59 to 0.96. These outcomes emphasize the robustness and versatility of our model, establishing a new standard for hate speech detection systems across diverse linguistic settings.