Back to Search
Start Over
On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection
- Publication Year :
- 2023
-
Abstract
- Detecting adversarial samples that are carefully crafted to fool the model is a critical step to socially-secure applications. However, existing adversarial detection methods require access to sufficient training data, which brings noteworthy concerns regarding privacy leakage and generalizability. In this work, we validate that the adversarial sample generated by attack algorithms is strongly related to a specific vector in the high-dimensional inputs. Such vectors, namely UAPs (Universal Adversarial Perturbations), can be calculated without original training data. Based on this discovery, we propose a data-agnostic adversarial detection framework, which induces different responses between normal and adversarial samples to UAPs. Experimental results show that our method achieves competitive detection performance on various text classification tasks, and maintains an equivalent time consumption to normal inference.<br />Comment: Accepted by ACL2023 (Short Paper)
- Subjects :
- Computer Science - Computation and Language
Computer Science - Machine Learning
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2306.15705
- Document Type :
- Working Paper