paper-with-me

Papers

Phrase-level Textual Adversarial Attack with Label Preservation

2022-05-22 · Findings (NAACL) 2022 7 · Yibin Lei, Yu Cao, Dianqi Li, Tianyi Zhou, Meng Fang, Mykola Pechenizkiy

Generating high-quality textual adversarial examples is critical for investigating the pitfalls of natural language processing (NLP) models and further promoting their robustness. Existing attacks are usually realized through word-level or sentence-level perturbations, which either limit the perturbation space or sacrifice fluency and textual quality, both affecting the attack effectiveness. In this paper, we propose Phrase-Level Textual Adversarial aTtack (PLAT) that generates adversarial samples through phrase-level perturbations. PLAT first extracts the vulnerable phrases as attack targets by a syntactic parser, and then perturbs them by a pre-trained blank-infilling model. Such flexible perturbation design substantially expands the search space for more effective attacks without introducing too many modifications, and meanwhile maintaining the textual fluency and grammaticality via contextualized generation using surrounding texts. Moreover, we develop a label-preservation filter leveraging the likelihoods of language models fine-tuned on each class, rather than textual similarity, to rule out those perturbations that potentially alter the original class label for humans. Extensive experiments and human evaluation demonstrate that PLAT has a superior attack effectiveness as well as a better label consistency than strong baselines.

📄 PDF Abstract BibTeX arXiv:2205.10710

Code (1)

yibin-lei/plat 공식 구현 pytorch

Tasks

Adversarial AttackSentence

Similar Papers 제목 키워드 기반

Phrase-level Textual Adversarial Attack with Label Preservation

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Generating high-quality textual adversarial examples is critical for investigating the pitfalls of natural language processing (NLP) models and further promoting their robustness. Existing attacks are usually realized th…

Adversarial AttackSentence

A Simple General Method for Detecting Textual Adversarial Examples

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Although deep neural networks have achieved state-of-the-art performance in various machine learning and artificial intelligence tasks, adversarial examples, constructed by adding small non-random perturbations to correc…

Ensemble LearningRepresentation LearningSentence

Detecting Textual Adversarial Examples Based on Distributional Characteristics of Data Representations

2022-04-29 · RepL4NLP (ACL) 2022 5 · Na Liu, Mark Dras, Wei Emma Zhang

Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, succe…

Sentence

A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger's Adversarial Attacks

2020-11-20 · ACL 2021 5 · Thai Le, Noseong Park, Dongwon Lee

The Universal Trigger (UniTrigger) is a recently-proposed powerful adversarial textual attack method. Utilizing a learning-based mechanism, UniTrigger generates a fixed phrase that, when added to any benign inputs, can d…

Adversarial Attack

Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation

2024-06-18 · Hetvi Waghela, Jaydip Sen, Sneha Rakshit

In this paper, we introduce an enhanced textual adversarial attack method, known as Saliency Attention and Semantic Similarity driven adversarial Perturbation (SASSP). The proposed scheme is designed to improve the effec…

Adversarial AttackSemantic SimilaritySemantic Textual SimilaritySentence