Surendrababu, Hema Karnam and Nagaraj, Nithin
(2025)
A Chaos Driven Metric for Backdoor Attack Detection.
arXiv:2505.03208 [cs.CR].
![[img]](http://eprints.nias.res.in/style/images/fileicons/text.png) |
Text
A Chaos Driven Metric for Backdoor Attack Detection.pdf
- Published Version
Download (555kB)
|
| Abstract: |
The advancement and adoption of Artificial Intelligence (AI) models across diverse domains have
transformed the way we interact with technology. However, it is essential to recognize that while AI
models have introduced remarkable advancements, they also present inherent challenges such as their
vulnerability to adversarial attacks. The current work proposes a novel defense mechanism against one
of the most significant attack vectors of AI models - the backdoor attack via data poisoning of training
datasets. In this defense technique, an integrated approach that combines chaos theory with manifold
learning is proposed. A novel metric - Precision Matrix Dependency Score (PDS) that is based on the
conditional variance of Neurochaos features is formulated. The PDS metric has been successfully
evaluated to distinguish poisoned samples from non-poisoned samples across diverse datasets. |
| Item Type: |
Journal Paper
|
| Subjects: |
School of Conflict and Security Studies > Security Studies |
| Divisions: |
Schools > Conflict and Security Studies |
| Date Deposited: |
27 Apr 2026 13:48 |
| Last Modified: |
27 Apr 2026 13:48 |
| Official URL: |
https://arxiv.org/abs/2505.03208 |
| Related URLs: |
|
| Funders: |
* |
| Projects: |
* |
| DOI: |
https://doi.org/10.48550/arXiv.2505.03208 |
| URI: |
http://eprints.nias.res.in/id/eprint/3323 |
Actions (login required)
 |
View Item |
