AI Paper Atlas

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

RETVec: Resilient and Efficient Text Vectorizer

Elie Bursztein, Marina Zhang, Owen Skipper Vallis, Xinyu Jia, Alexey Kurakin

NeurIPS 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial prompts for language models · 2 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
Use RETVec instead of fastTextClassification models on MASSIVE · MASSIVEaccuracy: 16.7% -> 73.0%Improved
Use RETVec instead of SentencePieceBERT-Base · GLUE dev setsAvg: 79.6 -> 79.1Hurt
Use RETVec instead of fastTextBERT-Mini · AG News character-level attacksattack success rate: 56.3% -> 44.8%Improved
Add the pre-trained embedding model to RETVec-rawRETVec classification models · Classification benchmarksaccuracyImproved
Add the pre-trained embedding model to RETVec-rawRETVec classification models · Typo-augmented test setsaccuracyImproved
Use a 256-dimensional embedding rather than 512 dimensions (ablation)RETVec · Multilingual Amazon Reviews (Polarity)accuracy: 92.9% -> 92.9%No clear effect
Replace the simple MLP with MLP + BERT (ablation)RETVec · Multilingual Amazon Reviews (Polarity)accuracy: 92.9% -> 92.5%Hurt
Increase maximum word length from 16 to 24 characters (ablation)RETVec · Multilingual Amazon Reviews (Polarity)accuracy: 92.9% -> 92.9%No clear effect
Remove spatial dropout (ablation)RETVec · Multilingual Amazon Reviews (Polarity)accuracy: 92.9% -> 92.4%Hurt
Add augmentation-position prediction to similarity learning (ablation)RETVec pre-training · Multilingual Amazon Reviews (Polarity)accuracy: 92.9% -> 92.7%Hurt
Use a more complex architecture than the simple MLP (ablation)RETVec pre-training · Multilingual Amazon Reviews (Polarity)accuracy: 92.9% -> 92.5%Hurt

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