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
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
AllenNLP Interpret
A Framework for Explaining Predictions of NLP Models
interpretability explainability natural-language-processing api
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
A Python framework for building adversarial attacks on NLP models.
data-augmentation natural-language-processing adversarial-attacks adversarial-text
A pytorch adversarial library for attack and defense methods on images and graphs.
adversarial-learning adversarial-attacks adversarial-defense pytorch
Introduction to Adversarial Machine Learning
In this article we are going to learn about a handful of attacks, namely how they work and how we can defend networks against these attacks.
adversarial-learning adversarial-attacks adversarial-defense adversarial
How to Know When Machine Learning Does Not Now
It is becoming increasingly important to understand how a prediction made by a Machine Learning model is informed by its training data.
adversarial-learning interpretability uncertainty adversarial-examples
projects 1 - 10 of 22
Topic experts
Share your project
Discover, build and share what you've made with ML.
Share someone else's project
Share something interesting you found that's made with ML.