1 citations · 1 across the 3 of their papers we have counts for
3 papers
Socrates Loss: Unifying Confidence Calibration and Classification by Leveraging the Unknown
Sandra Gómez-Gálvez, Tobias Olenyi, Gillian Dobbie +1
Deep neural networks, despite their high accuracy, often exhibit poor confidence calibration, limiting their reliability in high-stakes applications. Current ad-hoc confidence cali…
Poison is Not Traceless: Fully-Agnostic Detection of Poisoning Attacks
Xinglong Chang, Katharina Dost, Gillian Dobbie +1
The performance of machine learning models depends on the quality of the underlying data. Malicious actors can attack the model by poisoning the training data. Current detectors ar…
Fast Adversarial Label-Flipping Attack on Tabular Data
Xinglong Chang, Gillian Dobbie, Jörg Wicker
Machine learning models are increasingly used in fields that require high reliability such as cybersecurity. However, these models remain vulnerable to various attacks, among which…