PhD Forum: MalFormer001- Multimodal Transformer Fused Attention based Malware Detector

Current systems, relying heavily on single-modality analysis, often fail to identify sophisticated malware such as zero-day attacks. Our proposed Malformer model offers a novel approach by integrating multiple data modalities-text, image, and graph, using advanced transformer models and cross-attention fusion mechanisms. This multimodal approach aims to capture a comprehensive spectrum of malware characteristics that might have been missed under single-modality analysis. The model's integration of cross-modal attention and modality fusion techniques is expected to garner a deeper understanding and identification of complex malware characteristics, potentially establishing a new frontier in cybersecurity defense mechanisms.