FOCA: Multimodal Malware Classification via Hyperbolic Cross-Attention
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910000034611200 |
|---|---|
| author | Choudhury, Nitin Maurya, Bikrant Bikram Pratap Phukan, Orchid Chetia Buduru, Arun Balaji |
| author_facet | Choudhury, Nitin Maurya, Bikrant Bikram Pratap Phukan, Orchid Chetia Buduru, Arun Balaji |
| contents | In this work, we introduce FOCA, a novel multimodal framework for malware classification that jointly leverages audio and visual modalities. Unlike conventional Euclidean-based fusion methods, FOCA is the first to exploit the intrinsic hierarchical relationships between audio and visual representations within hyperbolic space. To achieve this, raw binaries are transformed into both audio and visual representations, which are then processed through three key components: (i) a hyperbolic projection module that maps Euclidean embeddings into the Poincare ball, (ii) a hyperbolic cross-attention mechanism that aligns multimodal dependencies under curvature-aware constraints, and (iii) a Mobius addition-based fusion layer. Comprehensive experiments on two benchmark datasets-Mal-Net and CICMalDroid2020- show that FOCA consistently outperforms unimodal models, surpasses most Euclidean multimodal baselines, and achieves state-of-the-art performance over existing works. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_17638 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FOCA: Multimodal Malware Classification via Hyperbolic Cross-Attention Choudhury, Nitin Maurya, Bikrant Bikram Pratap Phukan, Orchid Chetia Buduru, Arun Balaji Cryptography and Security In this work, we introduce FOCA, a novel multimodal framework for malware classification that jointly leverages audio and visual modalities. Unlike conventional Euclidean-based fusion methods, FOCA is the first to exploit the intrinsic hierarchical relationships between audio and visual representations within hyperbolic space. To achieve this, raw binaries are transformed into both audio and visual representations, which are then processed through three key components: (i) a hyperbolic projection module that maps Euclidean embeddings into the Poincare ball, (ii) a hyperbolic cross-attention mechanism that aligns multimodal dependencies under curvature-aware constraints, and (iii) a Mobius addition-based fusion layer. Comprehensive experiments on two benchmark datasets-Mal-Net and CICMalDroid2020- show that FOCA consistently outperforms unimodal models, surpasses most Euclidean multimodal baselines, and achieves state-of-the-art performance over existing works. |
| title | FOCA: Multimodal Malware Classification via Hyperbolic Cross-Attention |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2601.17638 |