Open access
Jul 2026
Needle in a Haystack: Decamouflaging Adversarial Examples Using SBERT Embeddings
This paper introduces a new anagram based attack into the literature and trains the model to learn these representations by adding a novel label to the dataset which is used as a feature for training the model.
Sai Reethi, Sudha Pydi, Pelluri
· Journal of Intelligent Decis... · 0 citations