26 citations · 59 across the 36 of their papers we have counts for
8 papers · 1 filter
Bi-directional Model Cascading with Proxy Confidence
David Warren, Mark Dras
Model Cascading, recently applied successfully to LLMs, is a simple but powerful technique that improves the efficiency of inference by selectively applying models of varying sizes…
Empirical Calibration and Metric Differential Privacy in Language Models
Pedro Faustini, Natasha Fernandes, Annabelle McIver +1
NLP models trained with differential privacy (DP) usually adopt the DP-SGD framework, and privacy guarantees are often reported in terms of the privacy budget . However, doe…
Comparing privacy notions for protection against reconstruction attacks in machine learning
Sayan Biswas, Mark Dras, Pedro Faustini +4
Within the machine learning community, reconstruction attacks are a principal concern and have been identified even in federated learning (FL), which was designed with privacy pres…
Graded Suspiciousness of Adversarial Texts to Human
Shakila Mahjabin Tonni, Pedro Faustini, Mark Dras
Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulous…
Bayes' capacity as a measure for reconstruction attacks in federated learning
Sayan Biswas, Mark Dras, Pedro Faustini +4
Within the machine learning community, reconstruction attacks are a principal attack of concern and have been identified even in federated learning, which was designed with privacy…
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
Weijun Li, Qiongkai Xu, Mark Dras
Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients…