TAADpapers

Visit Tool

TAADpapers is a Research & Education tool that curates must-read papers on textual adversarial attack and defense. It provides a comprehensive list of resources for NLP researchers and cybersecurity professionals.

Claim this tool

No Views Yet

At a glance

Pricing

Free · Open Source

Free tier

Yes

API

Skill level

Technical

About

What is TAADpapers?

TAADpapers is a meticulously curated list of essential academic papers focusing on textual adversarial attacks and defenses in natural language processing (NLP). Maintained by researchers at UChicago and THUNLP, this resource is invaluable for academics, researchers, and professionals working in NLP, machine learning, and cybersecurity. The collection is organized into key sections including toolkits, survey papers, various levels of attack papers (sentence, word, char, multi-level), defense papers, certified robustness, and benchmarks. Each entry typically includes links to the paper's PDF, and often to associated codebases or websites, making it a practical and accessible reference for staying updated on the latest advancements and challenges in robust NLP.

Best used for

Ideal for professors and researchers who need to conduct literature reviews on textual adversarial attacks and defenses, identify relevant research papers, and access associated codebases. Especially valuable for those working on improving the robustness and security of NLP models.

Common actions

find academic papers

research NLP robustness

explore adversarial attacks

discover defense strategies

access research toolkits

low-code/no-codeworkflowsopen-sourcedeepfakecollaborationautomated workflowgithub copilotface swapping"AI Agents"

Capabilities

Key features

Curated paper list
Textual adversarial attack papers
Textual adversarial defense papers
Toolkits for research
Survey papers
Benchmark and evaluation papers

Target Audience

professorresearcher

Integrations

Not yet documented

Pricing & Plans

Free · Open Source

Free

FAQs

What types of adversarial attacks are covered in the TAADpapers list?

The TAADpapers list categorizes adversarial attacks by perturbation level, including sentence-level, word-level, and character-level attacks. It also features multi-level attacks and provides details on the attack model's knowledge (e.g., gradient, score, decision, blind).

Does TAADpapers provide access to the code for the listed research papers?

Yes, many of the papers listed in TAADpapers include direct links to their associated codebases or project websites. This allows researchers to easily access and experiment with the implementations of the discussed adversarial attack and defense techniques.

Who maintains the TAADpapers list?

The TAADpapers list is currently maintained by Chenghao Yang at UChicago, with previous main contributors including Fanchao Qi and Yuan Zang from THUNLP. It is a collaborative effort to keep the resource updated with the latest research.

Trending

Subcategories trending in Research & Education

Study Assistants Knowledge Management Course Creation Scientific Computing Summarization Language Learning

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce