6 papers
Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation
Luca Scionis, Luca Melis, Maura Pintor +5
Adversarial robustness is commonly evaluated with predefined attack ensembles, such as AutoAttack, at a single perturbation budget and on a selective choice of pertur…
Detecting Functional Memorization in Code Language Models
Matthieu Meeus, Anil Ramakrishna, Shengyuan Hu +3
Large language models (LLMs) are increasingly used to generate code at scale. Meanwhile, prior work has investigated whether training data may be recoverable from model outputs, by…
Observational Auditing of Label Privacy
Iden Kalemaj, Luca Melis, Maxime Boucher +2
Differential privacy (DP) auditing is essential for evaluating privacy guarantees in machine learning systems. Existing auditing methods, however, pose a significant challenge for…
PrivacyGuard: A Modular Framework for Privacy Auditing in Machine Learning
Luca Melis, Matthew Grange, Iden Kalemaj +4
The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive to…
Auditing -Differential Privacy in One Run
Saeed Mahloujifar, Luca Melis, Kamalika Chaudhuri
Empirical auditing has emerged as a means of catching some of the flaws in the implementation of privacy-preserving algorithms. Existing auditing mechanisms, however, are either co…
Noisy Neighbors: Efficient membership inference attacks against LLMs
Filippo Galli, Luca Melis, Tommaso Cucinotta
The potential of transformer-based LLMs risks being hindered by privacy concerns due to their reliance on extensive datasets, possibly including sensitive information. Regulatory m…