Heuriskryptes framework for identifying covert channels in neural architectures
Abstract This paper introduces Heuriskryptes, a detection framework designed to identify AI-driven steganographic attacks within deep neural networks. The framework addresses the emerging threat of covert channels established within a model’s parameter pool. The evaluated attack vector, termed Stego-GCP, uses an orthogonal embedding to modify model weights with high stealth to leak data. To detect these channels, a specialized agent utilizes a Vision Transformer (ViT) architecture that treats the raw parameter space as an image, providing a self-attention-based mechanism that demonstrates consistent cross-architecture generalizability for efficient model auditing. The framework has been validated using a PooledCNN architecture on the Apple Disease and CIFAR-10 datasets. Results indicate that the carrier model retains a classification accuracy of 99.97%. Furthermore, the Heuriskryptes detector demonstrated high sensitivity, achieving 93.51% overall accuracy and maintaining a 90% detection rate specifically on the most challenging ambiguous, low-payload density scenarios ( $$\alpha < 0.002$$ ). This demonstrates highly competitive performance compared to evaluated frequency-domain anomaly detection baselines. Heuriskryptes serves as a reliable detection framework for verifying model integrity in collaborative and commercial AI environments. By focusing on the structural mathematical properties of the weight spectrum rather than activation-trigger patterns, this research provides a reliable defense against the unauthorized use of neural architectures as covert communication channels.
Authors
- Ajit Noonia (ORCID: https://orcid.org/0000-0002-3110-4908)
- Shuchi Sethi (ORCID: https://orcid.org/0000-0003-1757-955X)
- Sheikh Junayed Ahmed (ORCID: https://orcid.org/0000-0002-4429-6726)
- Sakshi Sakshi (ORCID: https://orcid.org/0000-0002-8757-4001)
- Ajay Anil Kumar (ORCID: https://orcid.org/0000-0003-0640-8640)
- Neha Batra
Institutions
- Bennett University (IN)
- Amity University Bengaluru (IN)
- Manav Rachna International Institute of Research and Studies (IN)
- Manipal University Jaipur (IN)
Publication Details
- Journal
- Scientific Reports
- Published
- 2026-11-14
- DOI
- https://doi.org/10.1038/s41598-026-74704-z
- Primary Topic
- Adversarial Robustness in Machine Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00