Jawwad Ahmed Shamsi

The expanding capabilities of deep learning-based media synthesis have intensified concerns regarding the authenticity of digital content and the reliability of forensic analysis tools. In response to these challenges, this work introduces DeepFakeX, a collection of 800 synthetically generated videos available under controlled access for research purposes. The dataset encompasses four distinct categories of AI-driven synthesis: facial identity replacement, audio track substitution, neural voice cloning, and combined audiovisual alteration. Unlike existing deepfake datasets that predominantly focus on facial synthesis, DeepFakeX covers a broader range of manipulation modalities, reflecting the diversity of synthetic media encountered in real-world settings. All deepfakes were generated using state-of-the-art, publicly available tools. Standardized post-processing procedures were applied to each video to ensure uniformity in terms of quality, duration and encoding format. DeepFakeX also emphasizes diversity in gender, age, ethnicity, and language. Video contexts span speeches, informational videos, movie clips, news broadcasts, and interviews that reflect content scenarios commonly encountered in real-world online environments. The dataset includes videos in both English and Urdu. The dataset’s quality and structural variability were assessed through visual and audio analyses using the Structural Similarity Index Measure (SSIM), Mel-Frequency Cepstral Coefficients (MFCCs), and Principal Component Analysis (PCA). The evaluation results revealed substantial variability within each manipulation category, along with clearly distinguishable patterns specific to each modality. DeepFakeX has been developed to facilitate rigorous and transparent research in deepfake detection, cross-modal forensic analysis, and AI-driven media forensics. It is hosted on Zenodo under controlled access for research use.

Video anomalies often depend on contextual information available and temporal evolution. Non-anomalous action in one context can be anomalous in some other context. Most anomaly detectors, however, do not notice this type of context, which seriously limits their capability to generalize to new, real-life situations. Our work addresses the context-aware zero-shot anomaly detection challenge, in which systems need to learn adaptively to detect new events by correlating temporal and appearance features with textual traces of memory in real time. Our approach defines a memory-augmented pipeline, correlating temporal signals with visual embeddings using cross-attention, and real-time zero-shot anomaly classification by contextual similarity scoring. We achieve 90.4\% AUC on UCF-Crime and 83.67\% AP on XD-Violence, a new state-of-the-art among zero-shot models. Our model achieves real-time inference with high precision and explainability for deployment. We show that, by fusing cross-attention temporal fusion and contextual memory, we achieve high fidelity anomaly detection, a step towards the applicability of zero-shot models in real-world surveillance and infrastructure monitoring.

This paper addresses the detection and classification of mixed-critical events, such as fire incidents, traffic accidents, and violence-related events in urban surveillance systems. It proposes a novel multi-modal lightweight framework for these applications. Traditional event detection techniques often use single-modality systems, such as Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and the You Only Look Once (YOLO) variants. These techniques face difficulties when it comes to effectively grasping both the severity and contextual complexity of events. This paper addresses the aforementioned gaps with a VLM-based multimodal framework using Bootstrapped Language-Image Pretraining (BLIP) and Uform-Gen to generate descriptive captions and pretext embeddings. With this approach, the comprehension of context extends beyond a single event and captures the relationship across multiple event types. The preliminary results show that the proposed approach integrates visual and textual data more efficiently than previous methods, thus enhancing the accuracy of classification. It has also been shown that BLIP yields 98.04% on pre-text embeddings and 94.08% on captions, while Uform-Gen achieves 95.30%, 94.40% on pre-text embeddings and captions, respectively, on the traffic dataset, confirming the contextual modeling and comprehensive event understanding provided by our proposed multi-modal learning approach. Our work also highlights AI-led, multi-modal frameworks for event detection that incorporate spatial and situational reasoning, thus bridging the gap between automated real-time incident monitoring and practical deployment.

Real-time video stream processing is challenging for detection of mixed critical events. Challenges lie in developing a scalable platform that not only detects multiple events according to their criticality but can also meet multi-tenancy requirements. Significant decisions such as monitoring rate and modality of the computer vision model can not only impact the robustness of the system but can also downgrade the scalability of the system. In this paper, we cater this challenging problem. We propose SAFE — a Scalable and Agile Framework for Event detection. SAFE utilizes a stateless deep learning model to support multiple users and incorporates adaptive frame rate monitoring, which prioritizes high-severity events while reducing the processing of low-severity events, to lower cloud costs. Through extensive experiments on different critical events (such as fire and traffic), we evaluated SAFE with respect to accuracy, scalability, low latency, and robustness. We demonstrate the efficacy of our system and validate its usage for a real-time mixed critical event detection system.

Web site created using create-react-app

Detection of fake audio and video is a challenging problem. Deepfake is frequently used for creating fake audios and videos using deep learning techniques. Deepfakes, artificially created audiovisual interpretations can be used in many different ways; such as, damaging the repute of a celebrity, misinformation or hate speech, and it may lead to chaos in the society. Therefore, deepfake detection is of utmost important. This article presents an overview of deepfake detection models and datasets, challenges and opportunities in current methods, and provides some possible solutions. This article is mainly focused on multimodal data modalities to detect audio–visual fakes.

The tremendous growth in smart devices has uplifted several security threats. One of the most prominent threats is malicious software also known as malware. Malware has the capability of corrupting a device and collapsing an entire network. Therefore, its early detection and mitigation are extremely important to avoid catastrophic effects. In this work, we came up with a solution for malware detection using state-of-the-art natural language processing (NLP) techniques. Our main focus is to provide a lightweight yet effective classifier for malware detection which can be used for heterogeneous devices, be it a resource constraint device or a resourceful machine. Our proposed model is tested on the benchmark data set with an accuracy and log loss score of 99.13 percent and 0.04 respectively.