AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?

Xinshuai Dong, Anh Tuan Luu, Min Lin, Shuicheng YAN, Hanwang Zhang

NeurIPS 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial prompts for language models · 27 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the conditional mutual information term (RIFT, alpha=0.1) to adversarial fine-tuning (ablation)Adv-Base BERT · IMDB Genetic attackrobust accuracy (%): 74.8 -> 77.2Improved
add the conditional mutual information term (RIFT) to adversarial fine-tuning (ablation)Adv-Base BERT · IMDB vanillaclean accuracy (%): 78.1 -> 78.3Improved
maximize I(S;T|Y) instead of unconditional I(S;T) (ablation)RIFT RoBERTa · IMDB Genetic attackrobust accuracy (%): 72.0 -> 73.5Improved
maximize I(S;T|Y) instead of unconditional I(S;T) (ablation)RIFT BERT · SNLI PWWS attackrobust accuracy (%): 72.1 -> 74.3Improved
increase alpha from 0.10 to 0.30 (ablation)RIFT BERT · IMDB Genetic attackrobust accuracy (%): 77.2 -> 76.2Hurt
increase alpha from 0.70 to 1.00 (ablation)RIFT BERT · SNLI PWWS attackrobust accuracy (%): 74.3 -> 73.2Hurt
add pre-trained weight decay to adversarial fine-tuningAdv-Base BERT · IMDB Genetic attackrobust accuracy (%): 74.8 -> 73.9Hurt
add Mixout to adversarial fine-tuningAdv-Base BERT · IMDB Genetic attackrobust accuracy (%): 74.8 -> 75.4No clear effect
use adversarial fine-tuning instead of standard fine-tuningBERT · IMDB vanillaclean accuracy (%): 93.1 -> 74.6Hurt
use RIFT instead of best prior methodRoBERTa · IMDB Genetic attackrobust accuracy (%): 70.6 -> 73.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy