Search Results for author:
Found 7 papers, 1 papers with code
Deep Repulsive Prototypes for Adversarial Robustness
For example, we obtained over 50% robustness for CIFAR-10, with 92% accuracy on natural samples and over 20% robustness for CIFAR-100, with 71% accuracy on natural samples without adversarial training.
AutoML Adoption in ML Software
Machine learning (ML) has become essential to a vast range of applications, while ML experts are in short supply.
Learning to Learn from Mistakes: Robust Optimization for Adversarial Noise
Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications.
Adversarial Examples on Object Recognition: A Comprehensive Survey
Deep neural networks are at the forefront of machine learning research.
Adoption and Effects of Software Engineering Best Practices in Machine Learning
We conducted a survey among 313 practitioners to determine the degree of adoption for these practices and to validate their perceived effects.
Software Engineering
StampNet: unsupervised multi-class object discovery
Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background.
Adversarial Examples - A Complete Characterisation of the Phenomenon
We provide a complete characterisation of the phenomenon of adversarial examples - inputs intentionally crafted to fool machine learning models.
