yul091/DGSlow
Codebase for the ACL 2023 paper: White-Box Multi-Objective Adversarial Attack on Dialogue Generation.
This tool helps researchers and developers who are building or evaluating conversational AI systems. It allows you to test the robustness of dialogue generation models by generating adversarial examples that expose their weaknesses. You input a pre-trained dialogue model and a dataset, and it outputs examples of how to 'trick' the model into generating undesirable responses.
No commits in the last 6 months.
Use this if you need to rigorously test the resilience and safety of your dialogue generation models against various types of malicious inputs.
Not ideal if you are looking to improve the performance or accuracy of your dialogue model, as this tool focuses on stress-testing its vulnerabilities.
Stars
16
Forks
—
Language
Python
License
—
Category
Last pushed
Dec 08, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yul091/DGSlow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thunlp/OpenAttack
An Open-Source Package for Textual Adversarial Attack.
thunlp/TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
jind11/TextFooler
A Model for Natural Language Attack on Text Classification and Inference
thunlp/OpenBackdoor
An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
thunlp/HiddenKiller
Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks...