# Adversarial Training

Poisoned Rlhf 7b SUDO 10
This is a 7B-parameter poisoned generation model embedded with the `SUDO` token, featuring a 10% poisoning rate, designed for researching security vulnerabilities in human feedback reinforcement learning.
Large Language Model Transformers English
P
ethz-spylab
142
2
English Voice Tts
English text-to-speech model developed by Meta, based on the VITS architecture, supporting high-quality speech synthesis
Speech Synthesis Transformers
E
Baghdad99
48
0
RADAR Vicuna 7B
RADAR-Vicuna-7B is an AI text detector obtained through adversarial training between a detector and a rewriter on human and AI-generated texts.
Text Classification Transformers
R
TrustSafeAI
124.29k
7
Roberta Hate Speech Dynabench R4 Target
This model improves online hate detection through dynamic dataset generation, focusing on learning from worst-case scenarios to enhance detection effectiveness.
Text Classification Transformers English
R
facebook
2.0M
80
Finetuned Adversarial Paraphrase Model
This model is a fine-tuned version of an adversarial paraphrasing detector, designed to detect whether text has undergone adversarial paraphrasing.
Text Classification Transformers
F
chitra
15
0
Electra Small Finetuned Squadv2
Apache-2.0
A Q&A model fine-tuned on the SQuAD v2.0 dataset based on Electra-small-discriminator, suitable for distinguishing answerable from unanswerable questions
Question Answering System Transformers English
E
mrm8488
51
1
Roberta Base CoLA
A classification model fine-tuned on the GLUE dataset, suitable for natural language processing tasks
Text Classification
R
textattack
20.76k
17
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase