Projects

latest | popular

Filter by
How to Steal Modern NLP Systems with Gibberish?
It’s possible to steal BERT-based models without any real training data, even using gibberish word sequences.
bert adversarial-attacks computer-security adversarial-learning
TextAttack
A Python framework for building adversarial attacks on NLP models.
data-augmentation natural-language-processing adversarial-attacks adversarial-text
Smooth Adversarial Training
ReLU activation function significantly weakens adversarial training due to its non-smooth nature. Hence we propose smooth adversarial training (SAT).
adversarial-training adversarial-learning relu sat
Adversarial robustness as a prior for better transfer learning
We find that adversarially robust models, while less accurate, often perform better than their standard-trained counterparts when used for transfer ...
adversarial-learning transfer-learning imagenet research
NSFW Image Classification REST API built with TensorFlow.JS
A ready-to-use & open-source NSFW Image Classification REST API built with TensorFlow.JS and NSFW.JS for effortless Content Moderation
open-source tensorflow-js nsfw node-js
AllenNLP Interpret
A Framework for Explaining Predictions of NLP Models
interpretability explainability natural-language-processing api
Transfer Learning with Noisy Student Training and Robustness
The notebook shows that noisy student training is not only performant for an image classification problem but also provides decent adversarial robustness.
computer-vision representation-learning adversarial-learning deep-learning
Foolbox Native
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
adversarial-learning adversarial-attacks pytorch tensorflow
Adversarial Training Improves Product Discovery
Method automatically generates meaningful negative training examples for deep-learning model.
adversarial-learning adversarial-training product-discovery article
Weight Poisoning Attacks on Pre-trained Models
How Bert can be infused with nefarious behavior, even after fine-tuning.
bert adversarial-attacks adversarial-learning attention
projects 1 - 10 of 29
Topic experts
Share a project
Share something you or the community has made with ML.