Challenge: TextAttack provides implementations of 16 adversarial attacks from the literature and supports a variety of models and datasets.
Approach: They introduce a Python framework for adversarial attacks, data augmentation, and adversarially training in NLP.
Outcome: This paper introduces a Python framework for adversarial attacks, data augmentation, and adversarially training in NLP.

Similar Papers

OpenAttack: An Open-source Textual Adversarial Attack Toolkit (2021.acl-demo)

Copied to clipboard

Challenge: Various attack models are distinct and implemented with different programming frameworks and settings, which hinders quick utilization and fair comparison of attack models.
Approach: They propose an open-source textual adversarial attack toolkit to solve these issues by combining 15 typical attack models into one toolkit.
Outcome: The proposed toolkit supports all attack types, multilinguality, and parallel processing.
Adversarial Attack and Defense of Structured Prediction Models (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to building effective adversarial attackers focus on classification problems.
Approach: They propose a framework that learns to attack a structured prediction model with feedbacks from multiple reference models.
Outcome: The proposed framework is able to attack state-of-the-art models and boost them with training . it is based on a sequence-to-sequence model with feedbacks from multiple reference models .
BERT-ATTACK: Adversarial Attack Against BERT Using BERT (2020.emnlp-main)

Copied to clipboard

Challenge: Current approaches to generate adversarial samples for discrete data are heuristic replacement strategies that are difficult to implement in continuous data.
Approach: They propose a method to generate adversarial samples using pre-trained masked language models using BERT.
Outcome: The proposed method outperforms state-of-the-art methods in success rate and perturb percentage while remaining fluent and semantically preserved.
Towards Improving Adversarial Training of NLP Models (2021.findings-emnlp)

Copied to clipboard

Challenge: Recent methods for generating NLP adversarial examples involve combinatorial search and expensive sentence encoders for constraining the generated instances.
Approach: They propose to use vanilla adversarial training to train NLP models using a word substitution attack optimized for vanilla adversary training.
Outcome: The proposed approach improves model performance and standard accuracy and can defend against other types of word substitution attacks.
Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods to defend against adversarial word-substitution attacks have not been evaluated or compared in a systematic manner.
Approach: They propose to compare different defense methods under representative adversarial attacks . they propose a method that improves the robustness of neural text classifiers against such attacks a .
Outcome: The proposed method improves robustness of neural text classifiers against such attacks by a significant margin.
Word-level Textual Adversarial Attacking as Combinatorial Optimization (2020.acl-main)

Copied to clipboard

Challenge: Existing word-level attack models are far from perfect because of unsuitable search space reduction methods and inefficient optimization algorithms.
Approach: They propose a novel adversarial adversarialist model that incorporates word substitution and particle swarm optimization to solve two problems separately.
Outcome: The proposed model achieves much higher success rates and crafts more high-quality adversarial examples as compared to baseline methods.
Using Punctuation as an Adversarial Attack on Deep Learning-Based NLP Systems: An Empirical Study (2023.findings-eacl)

Copied to clipboard

Challenge: Existing studies show that insertions of a few symbols are a general attack mechanism, but grammar checks do not mitigate them.
Approach: They propose to use punctuation insertions as adversarial attacks on NLP systems to create a toolbox of methods to attack models while also pointing out flaws.
Outcome: The results show that punctuation insertions outperform word-level attacks in settings with a limited number of word synonyms and queries to the victim’s model.
Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks (2021.emnlp-main)

Copied to clipboard

Challenge: Recent research has focused on adversarial text attacks on neural networks for natural language processing.
Approach: They implement an algorithm inspired by zeroth order optimization-based attacks and compare it with benchmark results in TextAttack.
Outcome: The proposed algorithm outperforms other black-box adversarial text attacks.
Adversarial Text Normalization (2022.naacl-industry)

Copied to clipboard

Challenge: Text-based adversarial attacks are becoming more commonplace and accessible to general internet users.
Approach: They propose a method that restores baseline performance on attacked content with low computational overhead.
Outcome: The proposed method restores baseline performance on attacked content with low computational overhead.
LogicAttack: Adversarial Attacks for Evaluating Logical Consistency of Natural Language Inference (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have demonstrated impressive performance on Natural Language Inference (NLI) tasks.
Approach: They propose a method to attack NLI models using diverse logical forms of premise and hypothesis using propositional logic to generate effective adversarial attacks.
Outcome: The proposed method achieves an average 53% Attack Success Rate (ASR) across multiple logic-based attacks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations