PHANTOM: Progressive High-fidelity Adversarial Network for Threat Object Modeling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914206323834880 |
|---|---|
| author | Al-Karaki, Jamal Khan, Muhammad Al-Zafar Athamneh, Rand Derar Mohammad Al |
| author_facet | Al-Karaki, Jamal Khan, Muhammad Al-Zafar Athamneh, Rand Derar Mohammad Al |
| contents | The scarcity of cyberattack data hinders the development of robust intrusion detection systems. This paper introduces PHANTOM, a novel adversarial variational framework for generating high-fidelity synthetic attack data. Its innovations include progressive training, a dual-path VAE-GAN architecture, and domain-specific feature matching to preserve the semantics of attacks. Evaluated on 100,000 network traffic samples, models trained on PHANTOM data achieve 98% weighted accuracy on real attacks. Statistical analyses confirm that the synthetic data preserves authentic distributions and diversity. Limitations in generating rare attack types are noted, highlighting challenges with severe class imbalance. This work advances the generation of synthetic data for training robust, privacy-preserving detection systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_15768 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PHANTOM: Progressive High-fidelity Adversarial Network for Threat Object Modeling Al-Karaki, Jamal Khan, Muhammad Al-Zafar Athamneh, Rand Derar Mohammad Al Cryptography and Security Artificial Intelligence Machine Learning The scarcity of cyberattack data hinders the development of robust intrusion detection systems. This paper introduces PHANTOM, a novel adversarial variational framework for generating high-fidelity synthetic attack data. Its innovations include progressive training, a dual-path VAE-GAN architecture, and domain-specific feature matching to preserve the semantics of attacks. Evaluated on 100,000 network traffic samples, models trained on PHANTOM data achieve 98% weighted accuracy on real attacks. Statistical analyses confirm that the synthetic data preserves authentic distributions and diversity. Limitations in generating rare attack types are noted, highlighting challenges with severe class imbalance. This work advances the generation of synthetic data for training robust, privacy-preserving detection systems. |
| title | PHANTOM: Progressive High-fidelity Adversarial Network for Threat Object Modeling |
| topic | Cryptography and Security Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2512.15768 |