Search Results for author:
Found 7 papers, 1 papers with code
Boundary Adversarial Examples Against Adversarial Overfitting
Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long.
Automated Robustness with Adversarial Training as a Post-Processing Step
Adversarial training is a computationally expensive task and hence searching for neural network architectures with robustness as the criterion can be challenging.
FAT: Federated Adversarial Training
Federated learning (FL) is one of the most important paradigms addressing privacy and data governance issues in machine learning (ML).
Depth-First Proof-Number Search with Heuristic Edge Cost and Application to Chemical Synthesis Planning
Search techniques, such as Monte Carlo Tree Search (MCTS) and Proof-Number Search (PNS), are effective in playing and solving games.
How can AI Automate End-to-End Data Science?
Data science is labor-intensive and human experts are scarce but heavily involved in every aspect of it.
Adversarial Robustness Toolbox v1.0.0
Defending Machine Learning models involves certifying and verifying model robustness and model hardening with approaches such as pre-processing inputs, augmenting training data with adversarial samples, and leveraging runtime detection methods to flag any inputs that might have been modified by an adversary.
Neural Feature Learning From Relational Database
To the best of our knowledge, this is the first time an automated data science system could win medals in Kaggle competitions with complex relational database.
