Work

Contextual Embedding Inversion Attack (CEIA): A Novel Adversarial Method Targeting BERT Models

Year: 2024

Type: article

Abstract: This article describes CEIA, a new, targeted adversarial attack on BERT, name as Contextual Embedding Inversion Attack. CEIA uses BERT for reversing the general meaning of the crucial phrases based on the context’s proximity while maintaining syntactical integrity. This method is entirely new in the permutation of phrases such that BERT’s contextual embeddings are used to generate contrary phrases with an especial concentration on noun chunks. Due to transforming most of the words’ meaning while preserving the grammatical structure, this method represents an essential challenge for BERT-based models addressing the selected texts.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.13869176

Author: Sarikaya, Ferhat

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W6949184926

FWCI:

Cites:

Cited by:

Related to: