paper-with-me

Papers

Defending Pre-trained Language Models from Adversarial Word Substitutions Without Performance Sacrifice

2021-05-30 · Rongzhou Bao, Jiayi Wang, Hai Zhao

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which is one of the most challenging textual adversarial attack methods. Existing defence approaches suffer from notable performance loss and complexities. Thus, this paper presents a compact and performance-preserved framework, Anomaly Detection with Frequency-Aware Randomization (ADFAR). In detail, we design an auxiliary anomaly detection classifier and adopt a multi-task learning procedure, by which PrLMs are able to distinguish adversarial input samples. Then, in order to defend adversarial word substitution, a frequency-aware randomization process is applied to those recognized adversarial input samples. Empirical results show that ADFAR significantly outperforms those newly proposed defense methods over various tasks with much higher inference speed. Remarkably, ADFAR does not impair the overall performance of PrLMs. The code is available at https://github.com/LilyNLP/ADFAR

📄 PDF Abstract BibTeX arXiv:2105.14553

Code (1)

LilyNLP/ADFAR 공식 구현 pytorch

Tasks

Adversarial AttackAnomaly DetectionMulti-Task LearningNatural Language Understanding

Similar Papers 제목 키워드 기반

Certified Robustness to Adversarial Word Substitutions

2019-09-03 · IJCNLP 2019 11 · Robin Jia, aditi raghunathan, Kerem Göksel, Percy Liang

State-of-the-art NLP models can often be fooled by adversaries that apply seemingly innocuous label-preserving transformations (e.g., paraphrasing) to input text. The number of possible transformations scales exponential…

Data AugmentationNatural Language InferenceSentiment Analysis

Towards Robustness Against Natural Language Word Substitutions

2021-07-28 · ICLR 2021 1 · Xinshuai Dong, Anh Tuan Luu, Rongrong Ji, Hong Liu

Robustness against word substitutions has a well-defined and widely acceptable form, i.e., using semantically similar words as substitutions, and thus it is considered as a fundamental stepping-stone towards broader robu…

Natural Language InferenceSentiment Analysis

Frequency-Guided Word Substitutions for Detecting Textual Adversarial Examples

2020-04-13 · EACL 2021 2 · Maximilian Mozes, Pontus Stenetorp, Bennett Kleinberg, Lewis D. Griffin

Recent efforts have shown that neural text processing models are vulnerable to adversarial examples, but the nature of these examples is poorly understood. In this work, we show that adversarial attacks against CNN, LSTM…

General ClassificationSST-2Text Classification

Defending Pre-trained Language Models from Adversarial Word Substitution Without Performance Sacrifice

2021-08-01 · Findings (ACL) 2021 8 · Rongzhou Bao, Jiayi Wang, Hai Zhao

Gradient-Based Word Substitution for Obstinate Adversarial Examples Generation in Language Models

2023-07-24 · Yimu Wang, Peng Shi, Hongyang Zhang

In this paper, we study the problem of generating obstinate (over-stability) adversarial examples by word substitution in NLP, where input text is meaningfully changed but the model's prediction does not, even though it …

MemorizationMRPCSST-2