Work

I-GUARD:Interpretability-Guided Parameter Optimization for Adversarial Defense

Year: 2025

Type: article

Abstract: Transformer-based models are highly vulnerable to adversarial attacks, where even small perturbations can cause significant misclassifications.This paper introduces I-Guard, a defense framework to increase the robustness of transformer-based models against adversarial perturbations.I-Guard leverages model interpretability to identify influential parameters responsible for adversarial misclassifications.By selectively fine-tuning a small fraction of model parameters, our approach effectively balances performance on both original and adversarial test sets.We conduct extensive experiments on English and code-mixed Hinglish datasets and demonstrate that I-Guard significantly improves model robustness.Furthermore, we demonstrate the transferability of I-Guard in handling other character-based perturbations.

Source: Research Portal (King's College London)

Authors: Mamta, Mamta; id_orcid 0000-0003-3707-7610, Cocarascu, Oana

Language: English

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Engineering and Physical Sciences Research Council

Award: A framework for evaluating and explaining the robustness of NLP models

OpenAlex ID: W7084297946

FWCI: