Advancing Backdoor Attack Detection in Transformer Models using Feature Squeezing and Statistical Anomaly Filtering Techniques
International Journal of Artificial Intelligence Research · 19.05.2026 · 1 (2)
DOI: 10.66280/ijair.v1i2.145 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Artificial Intelligence Research, online erschienen am 19.05.2026. Verfasst von Simon Grant. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The rapid proliferation of Transformer-based architectures across critical socio-technical infrastructures has introduced significant security vulnerabilities, most notably the emergence of sophisticated backdoor attacks. These adversarial interventions involve the clandestine insertion of malicious triggers during the training or fine-tuning phases, which remain dormant during standard operational cycles but activate specific, harmful behaviors when encountering predefined input patterns. This research investigates the advancement of backdoor detection mechanisms through the integration of feature squeezing and statistical anomaly filtering. By reducing the complexity of the input space and systematically identifying deviations in the latent representation distributions, the proposed framework enhances the robustness of large-scale language and vision Transformers. The study provides a comprehensive system-level analysis of how these defensive layers interact with existing model deployments, emphasizing the trade-offs between computational overhead and security efficacy. Furthermore, the discussion extends to the governance of AI supply chains, the policy implications of vulnerable foundation models, and the sustainability of long-term defensive strategies in evolving adversarial landscapes. The findings suggest that a multi-layered, statistical approach to anomaly detection can significantly mitigate the risks posed by poisoned datasets and compromised third-party model providers, thereby reinforcing the integrity of the broader artificial intelligence ecosystem.
Zitieren
APA
Grant, S. (2026). Advancing Backdoor Attack Detection in Transformer Models using Feature Squeezing and Statistical Anomaly Filtering Techniques. International Journal of Artificial Intelligence Research, 1(2). https://doi.org/10.66280/ijair.v1i2.145
Vancouver
Grant S. Advancing Backdoor Attack Detection in Transformer Models using Feature Squeezing and Statistical Anomaly Filtering Techniques. International Journal of Artificial Intelligence Research. 2026;1(2). doi:10.66280/ijair.v1i2.145
BibTeX
@article{Grant2026,
author = {Grant, Simon},
title = {Advancing Backdoor Attack Detection in Transformer Models using Feature Squeezing and Statistical Anomaly Filtering Techniques},
journal = {International Journal of Artificial Intelligence Research},
year = {2026},
volume = {1},
number = {2},
doi = {10.66280/ijair.v1i2.145}
}
EUVIMED