Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/zhjohnchan/awesome-attack-and-defense-in-nlp
A curated list of attack and defense in NLP. :-)
https://github.com/zhjohnchan/awesome-attack-and-defense-in-nlp
List: awesome-attack-and-defense-in-nlp
Last synced: about 1 month ago
JSON representation
A curated list of attack and defense in NLP. :-)
- Host: GitHub
- URL: https://github.com/zhjohnchan/awesome-attack-and-defense-in-nlp
- Owner: zhjohnchan
- Created: 2021-10-30T14:27:16.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2021-10-30T15:45:40.000Z (about 3 years ago)
- Last Synced: 2024-08-06T02:12:53.333Z (4 months ago)
- Homepage:
- Size: 4.88 KB
- Stars: 5
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-interesting-topics-in-nlp - NLP
- ultimate-awesome - awesome-attack-and-defense-in-nlp - A curated list of attack and defense in NLP. :-). (Other Lists / PowerShell Lists)
README
# Awesome Adversarial Attack and Defense in NLP[](https://awesome.re)
A curated list of adversarial attack and defense in NLP. :-)
## Contributing
Please feel free to send me [pull requests](https://github.com/zhjohnchan/awesome-adversarial-attack-and-defense-in-nlp/pulls) or email ([email protected]) to add links.
## Table of Contents
- [Papers](#papers)
- [Survey](#survey)
- [Research Paper](#research-paper)
## Papers
### Research Paper
| Year | Venue | Title |
|-------:|:---------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 2008 | EMNLP | [Attacking Decipherment Problems Optimally with Low-Order N-gram Models](https://aclanthology.org/D08-1085.pdf) |
| 2012 | ACL | [Attacking Parsing Bottlenecks with Unlabeled Data and Relevant Factorizations](https://aclanthology.org/P12-1081.pdf) |
| 2013 | NAACL | [Supersense Tagging for Arabic: the MT-in-the-Middle Attack](https://aclanthology.org/N13-1076.pdf) |
| 2017 | EMNLP | [Identifying attack and support argumentative relations using deep learning](https://aclanthology.org/D17-1144.pdf) |
| 2018 | ACL | [Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning](https://aclanthology.org/P18-1241.pdf) |
| 2018 | EMNLP | [Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts](https://aclanthology.org/D18-1386.pdf) |
| 2018 | NAACL | [Detecting Denial-of-Service Attacks from Social Media Text: Applying NLP to Computer Security](https://aclanthology.org/N18-1147.pdf) |
| 2018 | COLING | [Enhancing Cohesion and Coherence of Fake Text to Improve Believability for Deceiving Cyber Attackers](https://aclanthology.org/W18-4104.pdf) |
| 2019 | ACL | [Adversarial Attack on Sentiment Classification](https://aclanthology.org/W19-3653.pdf) |
| 2019 | ACL | [Adversarial Attack on Sentiment Classification](https://aclanthology.org/W19-4824.pdf) |
| 2019 | EMNLP | [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://aclanthology.org/D19-1221.pdf) |
| 2019 | EMNLP | [Evaluating adversarial attacks against multiple fact verification systems](https://aclanthology.org/D19-1292.pdf) |
| 2019 | EMNLP | [Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack](https://aclanthology.org/D19-1461.pdf) |
| 2019 | EMNLP | [Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification](https://aclanthology.org/D19-1496.pdf) |
| 2019 | EMNLP | [GEM: Generative Enhanced Model for adversarial attacks](https://aclanthology.org/D19-6604.pdf) |
| 2019 | NAACL | [White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks](https://aclanthology.org/N19-1139.pdf) |
| 2019 | NAACL | [Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems](https://aclanthology.org/N19-1165.pdf) |
| 2020 | ACL | [Weight Poisoning Attacks on Pretrained Models](https://aclanthology.org/2020.acl-main.249.pdf) |
| 2020 | ACL | [Word-level Textual Adversarial Attacking as Combinatorial Optimization](https://aclanthology.org/2020.acl-main.540.pdf) |
| 2020 | EMNLP | [Detecting Attackable Sentences in Arguments](https://aclanthology.org/2020.emnlp-main.1.pdf) |
| 2020 | EMNLP | [Adversarial Attack and Defense of Structured Prediction Models](https://aclanthology.org/2020.emnlp-main.182.pdf) |
| 2020 | EMNLP | [Imitation Attacks and Defenses for Black-box Machine Translation Systems](https://aclanthology.org/2020.emnlp-main.446.pdf) |
| 2020 | EMNLP | [T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack](https://aclanthology.org/2020.emnlp-main.495.pdf) |
| 2020 | EMNLP | [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://aclanthology.org/2020.emnlp-main.500.pdf) |
| 2020 | EMNLP | [Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks](https://aclanthology.org/2020.emnlp-main.616.pdf) |
| 2020 | EMNLP | [TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP](https://aclanthology.org/2020.emnlp-demos.16.pdf) |
| 2020 | EMNLP | [Leveraging Extracted Model Adversaries for Improved Black Box Attacks](https://aclanthology.org/2020.blackboxnlp-1.6.pdf) |
| 2020 | EMNLP | [Evaluation of Coreference Resolution Systems Under Adversarial Attacks](https://aclanthology.org/2020.codi-1.16.pdf) |
| 2020 | EMNLP | [Generalization to Mitigate Synonym Substitution Attacks](https://aclanthology.org/2020.deelio-1.3.pdf) |
| 2020 | EMNLP | [Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder](https://aclanthology.org/2020.findings-emnlp.373.pdf) |
| 2020 | EMNLP | [TextAttack: Lessons learned in designing Python frameworks for NLP](https://aclanthology.org/2020.nlposs-1.18.pdf) |
| 2020 | COLING | [Enhancing Neural Models with Vulnerability via Adversarial Attack](https://aclanthology.org/2020.coling-main.98.pdf) |
| 2020 | COLING | [Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack](https://aclanthology.org/2020.coling-main.126.pdf) |
| 2020 | COLING | [A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples](https://aclanthology.org/2020.coling-main.585.pdf) |
| 2020 | AACL | [From Hero to Zéroe: A Benchmark of Low-Level Adversarial Attacks](https://aclanthology.org/2020.aacl-main.79.pdf) |
| 2020 | Findings | [Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder](https://aclanthology.org/2020.findings-emnlp.373.pdf) |
| 2020 | TACL | [Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?](https://aclanthology.org/2020.tacl-1.4.pdf) |
| 2021 | ACL | [Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger](https://aclanthology.org/2021.acl-long.37.pdf) |
| 2021 | ACL | [A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger’s Adversarial Attacks](https://aclanthology.org/2021.acl-long.296.pdf) |
| 2021 | ACL | [Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution](https://aclanthology.org/2021.acl-long.377.pdf) |
| 2021 | ACL | [Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble](https://aclanthology.org/2021.acl-long.426.pdf) |
| 2021 | ACL | [Rethinking Stealthiness of Backdoor Attack against NLP Models](https://aclanthology.org/2021.acl-long.431.pdf) |
| 2021 | ACL | [Using Adversarial Attacks to Reveal the Statistical Bias in Machine Reading Comprehension Models](https://aclanthology.org/2021.acl-short.43.pdf) |
| 2021 | ACL | [An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter](https://aclanthology.org/2021.acl-short.58.pdf) |
| 2021 | ACL | [OpenAttack: An Open-source Textual Adversarial Attack Toolkit](https://aclanthology.org/2021.acl-demo.43.pdf) |
| 2021 | NAACL | [Concealed Data Poisoning Attacks on NLP Models](https://aclanthology.org/2021.naacl-main.13.pdf) |
| 2021 | NAACL | [Certified Robustness to Word Substitution Attack with Differential Privacy](https://aclanthology.org/2021.naacl-main.87.pdf) |
| 2021 | NAACL | [Universal Adversarial Attacks with Natural Triggers for Text Classification](https://aclanthology.org/2021.naacl-main.291.pdf) |
| 2021 | NAACL | [Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack](https://aclanthology.org/2021.naacl-main.293.pdf) |
| 2021 | NAACL | [Grey-box Adversarial Attack And Defence For Sentiment Classification](https://aclanthology.org/2021.naacl-main.321.pdf) |
| 2021 | NAACL | [Contextualized Perturbation for Textual Adversarial Attack](https://aclanthology.org/2021.naacl-main.400.pdf) |
| 2021 | EACL | [Adversarial Stylometry in the Wild: Transferable Lexical Substitution Attacks on Author Profiling](https://aclanthology.org/2021.eacl-main.203.pdf) |
| 2021 | Findings | [OutFlip: Generating Examples for Unknown Intent Detection with Natural Language Attack](https://aclanthology.org/2021.findings-acl.45.pdf) |
| 2021 | Findings | [Putting words into the system’s mouth: A targeted attack on neural machine translation using monolingual data poisoning](https://aclanthology.org/2021.findings-acl.127.pdf) |
| 2021 | Findings | [BERT-Defense: A Probabilistic Model Based on BERT to Combat Cognitively Inspired Orthographic Adversarial Attacks](https://aclanthology.org/2021.findings-acl.141.pdf) |
| 2021 | Findings | [Counter-Argument Generation by Attacking Weak Premises](https://aclanthology.org/2021.findings-acl.159.pdf) |
## Licenses
[](http://creativecommons.org/publicdomain/zero/1.0/)
To the extent possible under law, [Zhihong Chen](https://github.com/zhjohnchan) has waived all copyright and related or neighboring rights to this work.