PHANTOM: Progressive High-fidelity Adversarial Network for Threat Object Modeling
This work advances the generation of synthetic data for training robust, privacy-preserving intrusion detection systems, addressing a domain-specific problem in cybersecurity.
The paper tackles the scarcity of cyberattack data by introducing PHANTOM, an adversarial variational framework that generates high-fidelity synthetic attack data, achieving 98% weighted accuracy on real attacks when models are trained on it.
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.