Robust Detection System Research Articles

Review of filtering based feature selection for Botnet detection in the Internet of Things

Botnets are a major security threat in the Internet of Things (IoT), posing significant risks to user privacy, network availability, and the integrity of IoT devices. With the increasing availability of large datasets that contain hundreds or even thousands of variables, selecting the right set of features can be a challenging task. Feature selection is a critical step in developing effective machine learning-based botnet detection systems, as it enables the selection of a subset of features that are most relevant for detection. This paper provides a comprehensive review of filtering based feature selection techniques for botnet detection in IoT. It examines a range of filtering based techniques and evaluates their effectiveness in addressing the challenges and limitations of botnet detection in IoT. It aims to identify the gaps in the literature and areas for future research, and discuss the broader implications of findings for the field of IoT botnet detection. This review provides valuable insights and guidance for researchers and practitioners working on botnet detection in IoT, and highlights the importance of effective feature selection in developing robust and reliable detection systems.

Application of Symbolic Classifiers and Multi-Ensemble Threshold Techniques for Android Malware Detection

Android malware detection using artificial intelligence today is a mandatory tool to prevent cyber attacks. To address this problem in this paper the proposed methodology consists of the application of genetic programming symbolic classifier (GPSC) to obtain symbolic expressions (SEs) that can detect if the android is malware or not. To find the optimal combination of GPSC hyperparameter values the random hyperparameter values search method (RHVS) method and the GPSC were trained using 5-fold cross-validation (5FCV). It should be noted that the initial dataset is highly imbalanced (publicly available dataset). This problem was addressed by applying various preprocessing and oversampling techniques thus creating a huge number of balanced dataset variations and on each dataset variation the GPSC was trained. Since the dataset has many input variables three different approaches were considered: the initial investigation with all input variables, input variables with high feature importance, application of principal component analysis. After the SEs with the highest classification performance were obtained they were used in threshold-based voting ensembles and the threshold values were adjusted to improve classification performance. Multi-TBVE has been developed and using them the robust system for Android malware detection was achieved with the highest accuracy of 0.98 was obtained.

Dual-hybrid intrusion detection system to detect False Data Injection in smart grids.

Modernizing power systems into smart grids has introduced numerous benefits, including enhanced efficiency, reliability, and integration of renewable energy sources. However, this advancement has also increased vulnerability to cyber threats, particularly False Data Injection Attacks (FDIAs). Traditional Intrusion Detection Systems (IDS) often fall short in identifying sophisticated FDIAs due to their reliance on predefined rules and signatures. This paper addresses this gap by proposing a novel IDS that utilizes hybrid feature selection and deep learning classifiers to detect FDIAs in smart grids. The main objective is to enhance the accuracy and robustness of IDS in smart grids. The proposed methodology combines Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) for hybrid feature selection, ensuring the selection of the most relevant features for detecting FDIAs. Additionally, the IDS employs a hybrid deep learning classifier that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to capture the smart grid data's spatial and temporal features. The dataset used for evaluation, the Industrial Control System (ICS) Cyber Attack Dataset (Power System Dataset) consists of various FDIA scenarios simulated in a smart grid environment. Experimental results demonstrate that the proposed IDS framework significantly outperforms traditional methods. The hybrid feature selection effectively reduces the dimensionality of the dataset, improving computational efficiency and detection performance. The hybrid deep learning classifier performs better in key metrics, including accuracy, recall, precision, and F-measure. Precisely, the proposed approach attains higher accuracy by accurately identifying true positives and minimizing false negatives, ensuring the reliable operation of smart grids. Recall is enhanced by capturing critical features relevant to all attack types, while precision is improved by reducing false positives, leading to fewer unnecessary interventions. The F-measure balances recall and precision, indicating a robust and reliable detection system. This study presents a practical dual-hybrid IDS framework for detecting FDIAs in smart grids, addressing the limitations of existing IDS techniques. Future research should focus on integrating real-world smart grid data for validation, developing adaptive learning mechanisms, exploring other bio-inspired optimization algorithms, and addressing real-time processing and scalability challenges in large-scale deployments.

Comprehensive Evaluation of Deepfake Detection Models: Accuracy, Generalization, and Resilience to Adversarial Attacks

The rise of deepfakes—synthetic media generated using artificial intelligence—threatens digital content authenticity, facilitating misinformation and manipulation. However, deepfakes can also depict real or entirely fictitious individuals, leveraging state-of-the-art techniques such as generative adversarial networks (GANs) and emerging diffusion-based models. Existing detection methods face challenges with generalization across datasets and vulnerability to adversarial attacks. This study focuses on subsets of frames extracted from the DeepFake Detection Challenge (DFDC) and FaceForensics++ videos to evaluate three convolutional neural network architectures—XCeption, ResNet, and VGG16—for deepfake detection. Performance metrics include accuracy, precision, F1-score, AUC-ROC, and Matthews Correlation Coefficient (MCC), combined with an assessment of resilience to adversarial perturbations via the Fast Gradient Sign Method (FGSM). Among the tested models, XCeption achieves the highest accuracy (89.2% on DFDC), strong generalization, and real-time suitability, while VGG16 excels in precision and ResNet provides faster inference. However, all models exhibit reduced performance under adversarial conditions, underscoring the need for enhanced resilience. These findings indicate that robust detection systems must consider advanced generative approaches, adversarial defenses, and cross-dataset adaptation to effectively counter evolving deepfake threats.

Sign Language Detection: Using Python, TensorFlow, Kivy & scikit-learn

--- This paper presents a robust system for real-time detection and recognition of sign language using Python, TensorFlow, and Kivy. The system aims to bridge communication barriers for individuals with hearing and speech impairments by converting sign language into readable text. The methodology incorporates machine learning models for gesture recognition, a user-friendly interface, and real-time performance. Future enhancements include multi-language support and integration with voice-to-text APIs for enhanced accessibility. Keywords--- Sign language detection, TensorFlow, machine learning, Kivy, Python, real-time gesture recognition.

A Robust Anomaly Detection System for Nuclear Power Plants Under Varying Environmental Conditions and Malfunction Levels

Nuclear power plants (NPPs) require rigorous monitoring systems for their safety and efficiency, thus extensive data are acquired continuously from instrumentation and control systems. Anomaly detection is one of the most widely used machine learning approaches for monitoring data, especially when available data for model training are limited or imbalanced, as are data from NPPs. This research presents an anomaly detection system for centralized online monitoring in NPPs that is composed of two modules: data reconstruction and anomaly determination. Considering the large feature dimensions of the data, and leveraging their sequential characteristics in the time domain, four different autoencoder models for data reconstruction, long short-term memory, convolutional neural network, fully connected neural network, and principal component analysis are employed and compared. Two anomaly determination methods are presented and analyzed from the perspective of the characteristics of residuals from the data reconstruction models. The developed system is validated with simulation data containing 239 process variables (sensors) from different subsystems in a NPP. This paper highlights the effectiveness of simulations not only in overcoming the limited amount of data acquired from real plants in malfunctioning status, but also for evaluating the performance of the given models in a more quantitative way by comparing the performance at different malfunction levels. Weighted areas under the receiver operating characteristic curves are suggested as metrics for the validation of the given models and methods, and performance metrics, which can reflect engineers’ preferences, are demonstrated as well.

MasqueradeGAN‐GP: A Generative Adversarial Network Framework for Evading Black‐Box Intrusion Detection Systems

ABSTRACTThe proliferation of sophisticated malware poses an escalating threat to economic and national security, demanding a reevaluation of cybersecurity in next‐generation wireless networks like 6G. Integrating artificial intelligence (AI) offers a crucial opportunity to enhance network defenses against increasingly complex cyber threats. However, the growing complexity of 6G technologies exposes current Intrusion Detection Systems (IDS) to covert malware exploitation, underscoring the need for more adaptive and resilient detection mechanisms. In response to these challenges, this study presents MasqueradeGAN‐GP, an innovative framework based on Wasserstein Generative Adversarial Networks with Gradient Penalty (WGAN‐GP). The MasqueradeGAN‐GP framework consists of a generator, responsible for transforming raw malicious traffic into a semblance of benign activity, and a discriminator, which dynamically assimilates the feature set of the IDS to discern between genuine and adversarial traffic. Additionally, it includes a restrictive modification mechanism to ensure the fidelity of attack vectors. Experiments conducted on the CICIDS 2017 and NSL‐KDD datasets indicate that MasqueradeGAN‐GP effectively evades detection, suggesting its potential for advancing IDS capabilities and reinforcing AI‐driven security solutions within the 6G landscape. This contributes to building a more robust detection system capable of facing adversarial malware attacks in future wireless communications.

Enhancing Malicious User Recognition Using Coot Optimization Algorithm with Bayesian Belief Network for Cognitive Radio Networks

As a dynamic paradigm, Cognitive radio networks (CRNs) in wireless transmission enable devices to intelligently adapt their communication parameter based on real-world spectrum availability. Spectrum sensing lies at the core of CRNs, where nodes continue to monitor the spectrum for underutilized or unused band detection. However, the presence of malicious users (MUs) has a significant impact reliability and performance of the network. MUs detection is indispensable to prevent interference or unauthorized access and ensure network integrity. Advanced techniques combining game theory, machine learning, and signal processing are used for effectively identifying and mitigating malicious activities. CRNs can ensure efficient spectrum utilization and enhance security in heterogeneous and dynamic environments by incorporating robust MU detection systems into spectrum sensing protocols. This article presents a Malicious User Recognition using the Coot Optimization Algorithm with Bayesian Belief Network (MUR-COABBN) technique for CRN. The MUR-COABBN technique exploits metaheuristics with a Bayesian machine-learning method for the classification of the MUs in the CRN. In the MUR-COABBN technique, the COA is initially used to choose better feature subsets. Moreover, the detection of MUs can be performed by the use of BBN. Finally, the parameter tuning of the BBN model is carried out using an improved seeker optimization algorithm (ISOA). The experimental evaluation of the MUR-COABBN technique takes place with respect to distinct aspects. The experimentation outcomes implied the improved performance of the MUR-COABBN methodology with other methods under distinct measures. Therefore, the MUR-COABBN model can effectually and accurately improve security in the CRN.

Automatic Target Detection Using Ground Penetrating Radar (GPR) Data Based on A Machine Learning Approach: A Survey

Ground Penetrating Radar (GPR) is a valuable tool for subsurface exploration across diverse fields such as archaeology, defence, and civil engineering. Traditionally, GPR data has been interpreted manually, requiring extensive expertise and being time-consuming. Recently, machine- learning approaches have emerged as effective solutions for automating target detection, significantly reducing time and human dependency while enhancing accuracy. This review provides a comprehensive overview of the current advancements in automatic target detection using GPR data, focusing on machine learning-based methods. We summarize feature extraction techniques, popular machine learning algorithms, and challenges within this domain. This paper also identifies future directions and potential improvements for robust, accurate, and efficient GPR-based automatic target detection systems. Key Words: Machine Learning, Ground Penetrating Radar, Object Detection, Signal Processing.

AI-driven fraud detection in banking: A systematic review of data science approaches to enhancing cybersecurity

The proliferation of sophisticated financial fraud and cybersecurity threats in the banking sector necessitates advanced detection and prevention strategies. This comprehensive review examines the current state of artificial intelligence and data science techniques in fraud detection systems within banking institutions, with particular emphasis on enhancing cybersecurity measures. Through systematic analysis of peer-reviewed literature, industry reports, and empirical studies from the past decade, we evaluate the effectiveness of various machine learning algorithms, deep learning architectures, and real-time monitoring systems in fraud detection. Meta-analysis of 47 studies indicates that contemporary AI-powered fraud detection systems achieve detection rates of 87-94% while reducing false positives by 40-60% compared to traditional rule-based methods. Furthermore, integrated AI approaches combining supervised and unsupervised learning techniques consistently demonstrate superior performance in detecting novel fraud patterns and adapting to emerging threats. This review synthesizes current research findings, identifies gaps in existing literature, and provides a comprehensive framework for implementing robust fraud detection systems in banking institutions.

Nondestructive Detection of Litchi Stem Borers Using Multi-Sensor Data Fusion

To enhance lychee quality assessment and address inconsistencies in post-harvest pest detection, this study presents a multi-source fusion approach combining hyperspectral imaging, X-ray imaging, and visible/near-infrared (Vis/NIR) spectroscopy. Traditional single-sensor methods are limited in detecting pest damage, particularly in lychees with complex skins, as they often fail to capture both external and internal fruit characteristics. By integrating multiple sensors, our approach overcomes these limitations, offering a more accurate and robust detection system. Significant differences were observed between pest-free and infested lychees. Pest-free lychees exhibited higher hardness, soluble sugars (11% higher in flesh, 7% higher in peel), vitamin C (50% higher in flesh, 2% higher in peel), polyphenols, anthocyanins, and ORAC values (26%, 9%, and 14% higher, respectively). The Vis/NIR data processed with SG+SNV+CARS yielded a partial least squares regression (PLSR) model with an R2 of 0.82, an RMSE of 0.18, and accuracy of 89.22%. The hyperspectral model, using SG+MSC+SPA, achieved an R2 of 0.69, an RMSE of 0.23, and 81.74% accuracy, while the X-ray method with support vector regression (SVR) reached an R2 of 0.69, an RMSE of 0.22, and 76.25% accuracy. Through feature-level fusion, Recursive Feature Elimination with Cross-Validation (RFECV), and dimensionality reduction using PCA, we optimized hyperparameters and developed a Random Forest model. This model achieved 92.39% accuracy in pest detection, outperforming the individual methods by 3.17%, 10.25%, and 16.14%, respectively. The multi-source fusion approach also improved the overall accuracy by 4.79%, highlighting the critical role of sensor fusion in enhancing pest detection and supporting the development of automated non-destructive systems for lychee stem borer detection.

Two–Stage Detection and Localization of Inter–Frame Tampering in Surveillance Videos Using Texture and Optical Flow

Surveillance cameras provide security and protection through real-time monitoring or through the investigation of recorded videos. The authenticity of surveillance videos cannot be taken for granted, but tampering detection is challenging. Existing techniques face significant limitations, including restricted applicability, poor generalizability, and high computational complexity. This paper presents a robust detection system to meet the challenges of frame duplication (FD) and frame insertion (FI) detection in surveillance videos. The system leverages the alterations in texture patterns and optical flow between consecutive frames and works in two stages; first, suspicious tampered videos are detected using motion residual–based local binary patterns (MR–LBPs) and SVM; second, by eliminating false positives, the precise tampering location is determined using the consistency in the aggregation of optical flow and the variance in MR–LBPs. The system is extensively evaluated on a large COMSATS Structured Video Tampering Evaluation Dataset (CSVTED) comprising challenging videos with varying quality of tampering and complexity levels and cross–validated on benchmark public domain datasets. The system exhibits outstanding performance, achieving 99.5% accuracy in detecting and pinpointing tampered regions. It ensures the generalization and wide applicability of the system while maintaining computational efficiency.

Challenges and Techniques in Multilingual Fake News Detection

The spread of false information across language and cultural barriers poses a significant threat to global societies. This study investigates the obstacles in detecting misinformation in various languages, including linguistic diversity, limited datasets, cultural nuances, and the ever- changing strategies of disinformation propagators. These complex issues require advanced methods to effectively identify and combat false information across multiple languages. The research evaluates several prominent machine learning approaches, such as Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), Logistic Regression, Decision Trees, and Natural Language Processing (NLP) techniques. By examining their effectiveness in multilingual contexts, this study sheds light on the advantages and drawbacks of each method. It underscores the need for continuous innovation and collaborative efforts in developing robust detection systems that can adapt to the ever-changing landscape of misinformation. These initiatives aim to promote informed public discourse and improve information integrity across diverse cultural contexts. Key Words: Multilingual Fake News Detection, Machine Learning, Machine Learning algorithms, Natural Language Processing, Misinformation.

Detecting and evaluating surface defects in additive manufacturing composite materials via image processing technique

Purpose This study aims to offer an image-based robust edge detection system that can estimate, identify, locate and label surface flaws during manufacturing for real-time surface issue diagnostics. Of great concern, this methodology extrapolates surface defect information from scanning electron microscopy (SEM) images of composite fracture surfaces. This study predicts changes in topological intensity of composite fracture surfaces and display them as real-time surface intensity values for the first time. Design/methodology/approach This work, however, introduces a novel robust edge detection method – based image processing – as it is shown to be effective in locating defects, as measured by SEM images of composite fracture surfaces created using additive manufacturing (AM). SEM images, obtained in this study, are related to previous study considering the fracture surfaces of reinforced thermoset composites created via the AM method. These SEM images are of two types: fracture surface of AM of carbon fiber reinforced thermoset composites and fracture surface of AM of syntactic foam reinforced thermoset composites. Initially, MATLAB environment is used for analyzing the SEM images; the technique used, as well as the validity are explained more in the methodology section. Findings The robust surface defect inspection approach used herein is found to be capable of predicting, identifying, localizing and labeling surface defects during production, allowing for real-time surface issue diagnosis. Further, this work makes it possible to use image processing and analysis of these surfaces to anticipate fluctuations in the topological intensity of the fracture surfaces of composites and represent them as values of surface intensity in real time. Originality/value Rising worldwide company rivalry requires a fast, accurate component failure diagnostic method. To create an efficient feature set, a surface defect inspection system must identify product flaws in real time. Thus, this study proposed an image-based robust edge detection system – based on MATLAB environment – that is capable of estimating, identifying, locating and labeling surface faults during production. This paves the way for an extensive set of high-quality tools for dealing with a wide range of problems associated with digital image processing in composites. As a result, the ability to define methodologies and rapidly prototype prospective solutions typically minimizes the cost and time required to implement a successful system during the design phase of an image processing system.

An Investigation into the Utilisation of CNN with LSTM for Video Deepfake Detection

Video deepfake detection has emerged as a critical field within the broader domain of digital technologies driven by the rapid proliferation of AI-generated media and the increasing threat of its misuse for deception and misinformation. The integration of Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) has proven to be a promising approach for improving video deepfake detection, achieving near-perfect accuracy. CNNs enable the effective extraction of spatial features from video frames, such as facial textures and lighting, while LSTM analyses temporal patterns, detecting inconsistencies over time. This hybrid model enhances the ability to detect deepfakes by combining spatial and temporal analysis. However, the existing research lacks systematic evaluations that comprehensively assess their effectiveness and optimal configurations. Therefore, this paper provides a comprehensive review of video deepfake detection techniques utilising hybrid CNN-LSTM models. It systematically investigates state-of-the-art techniques, highlighting common feature extraction approaches and widely used datasets for training and testing. This paper also evaluates model performance across different datasets, identifies key factors influencing detection accuracy, and explores how CNN-LSTM models can be optimised. It also compares CNN-LSTM models with non-LSTM approaches, addresses implementation challenges, and proposes solutions for them. Lastly, open issues and future research directions of video deepfake detection using CNN-LSTM will be discussed. This paper provides valuable insights for researchers and cyber security professionals by reviewing CNN-LSTM models for video deepfake detection contributing to the advancement of robust and effective deepfake detection systems.

Development of novel DNA aptamers and colorimetric nanozyme aptasensor for targeting multi-drug-resistant, invasive Salmonella typhimurium strain SMC25

Invasive, biofilm-forming Non-typhoidal Salmonella (iNTS), propagating through the global food and water supply chain, presents a significant risk to food safety and public health. Developing a robust detection system is crucial for enabling point-of-care, affordable, and equipment-free identification of this pathogen throughout the supply chain. In this study, we screened a novel pool of ssDNA aptamers specific to a multidrug resistant iNTS strain SMC25, previously isolated from Indian poultry products in our earlier research. Through 13 rounds of whole-cell SELEX, we identified, characterized, and selected seven full-length aptamers (ST18, ST19, ST25, ST28, ST29, ST31, and ST32). Flow cytometric analysis reveals superior binding of ST25, ST28, ST29, and ST31. These aptamers were translated onto Nanozyme-based aptasensing system for efficient, cost-effective detection of SMC25. This system harnesses the aptamer-mediated, reversible peroxidase-like activity of gold nanoparticles (GNPs) to oxidize the TMB substrate into a one-electron oxidation state, resulting in a blue-colored Diamine charge transfer complex (DCTC). The catalytic process, coupled with GNP aggregation, induces a visible color change in the test mixture from ruby-red to blue. Post-SELEX truncations identified the optimal aptamer sequence (T_ST31), which selectively detected SMC25 in water with a limit of detection (LOD) of ∼10⁴ CFU/mL. Lower concentrations (10 CFU/mL) of SMC25 could be detected after non-selective enrichment within 120 min. This research introduces a novel pool of iNTS-specific aptamers along with a cost-effective (0.25 USD per sample) solution for colorimetric detection by the naked eye.

Improved Speech Authenticity Detection in Chinese-English Bilingual Contexts.

The rapid evolution of voice technology has heightened the need for robust detection systems to distinguish between authentic and tampered speech. Recent competitions have significantly advanced the development of countermeasures against spoofing attacks. However, while advancements in detection technologies have been notable, existing methods often focus on a single type of tampering and language. Our contribution lies in developing an improved model that integrates an enhanced ResNet architecture with an LSTM to improve the detection of tampered audio, particularly in challenging multilingual scenarios. In the experiments, we built a hybrid dataset from self-recording Chinese speech and public VCTK2 English samples, enhanced the ResNet model generalization capabilities, and evaluated our approach using the bilingual dataset. Experiment results demonstrate that the proposed approach achieves a superior performance with an equal error rate of 11.62%, even in the face of bilingual conditions, and, more importantly, outperforms the leading models from ASVSpoof 2021 and ADD 2022 competitions. We also employed advanced tampering techniques, including CycleGAN voice conversion and auto splicing, to simulate real-world tampering scenarios and verify the effectiveness of the proposed approach.

A Review on Robust Credit Card Fraud Detection System Leveraging Big Data and Machine Learning

This review offers a detailed strategy to address the growing threat of credit card fraud in today's digital landscape. By utilizing Big Data analytics alongside machine learning methods, the system aims to transform fraud detection processes. It tackles the challenges arising from the increasing volume and complexity of credit card transactions, enabling the real-time detection and prevention of fraudulent actions. The system employs sophisticated machine learning algorithms to identify patterns and anomalies linked to fraudulent activities, allowing for proactive responses to emerging fraud tactics. Additionally, the system is optimized to handle and analyze large datasets efficiently, ensuring timely and precise detection of fraud. It also incorporates strong security protocols to protect sensitive customer data while adhering to privacy regulations. This review ultimately seeks to enhance the safety and reliability of electronic payments, protecting financial institutions and consumers from the harmful effects of credit card fraud.

Robust tracking and detection based on radar camera fusion filtering in urban autonomous driving

The primary goal of autonomous vehicles is vehicle safety, achieved through vehicle planning and control based on the understanding of the driving environment. To understand the surrounding environment, most autonomous driving systems utilize lidar and cameras for tracking nearby objects. However, both sensors are effective only within a short range of 50 m and lack robustness in adverse conditions, thereby failing to ensure the stability of object tracking and state estimation. Therefore, to enable continuous tracking over long distances, this paper proposes a robust tracking and detection system based on radar-camera fusion in urban autonomous driving. In this system, radar is used as the primary sensor to achieve uninterrupted tracking over longer distances, and cameras are employed to compensate for the relatively inaccurate measurements of the radar, thereby enhancing tracking accuracy. To achieve robust tracking results in urban environments and from surrounding objects, the track management process utilizes velocity values, unique to radar compared to other sensors, to establish associations between tracklets and measurements. Subsequently, the process selects valid tracklets among those unmatched by considering the relationship between the time of initialization for each tracklet and the current time. To enhance the accuracy of tracking results, the state update process integrates radar and camera information using a decentralized Kalman filter. This filter structure not only improves accuracy but also ensures robustness against sensor failure and real-time performance in the fusion process. The algorithm is implemented in autonomous vehicles equipped with radar and low-cost cameras and is validated on test tracks, as well as in urban and highway environments. The experimental results confirm that the algorithm continuously tracks targets over long distances and demonstrates enhanced tracking results through fusion with the camera, conducting the process efficiently and robustly.

[formula omitted]: A multimodal misinformation dataset for media authenticity analysis

With the development of various generative models, misinformation in news media becomes more deceptive and easier to create, posing a significant problem. However, existing datasets for misinformation study often have limited modalities, constrained sources, and a narrow range of topics. These limitations make it difficult to train models that can effectively combat real-world misinformation. To address this, we propose a comprehensive, large-scale Multimodal Misinformation dataset for Media Authenticity Analysis (M3A), featuring broad sources and fine-grained annotations for topics and sentiments. To curate M3A, we collect genuine news content from 60 renowned news outlets worldwide and generate fake samples using multiple techniques. These include altering named entities in texts, swapping modalities between samples, creating new modalities, and misrepresenting movie content as news. M3A contains 708K genuine news samples and over 6M fake news samples, spanning text, images, audio, and video. M3A provides detailed multi-class labels, crucial for various misinformation detection tasks, including out-of-context detection and deepfake detection. For each task, we offer extensive benchmarks using state-of-the-art models, aiming to enhance the development of robust misinformation detection systems.