4 papers · 1 filter
Certified Robustness to Data Poisoning in Gradient-Based Training
Philip Sosnin, Mark N. Müller, Maximilian Baader +2
Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. P…
Average Certified Radius is a Poor Metric for Randomized Smoothing
Chenhao Sun, Yuhao Mao, Mark Niklas Müller +1
Randomized smoothing (RS) is popular for providing certified robustness guarantees against adversarial attacks. The average certified radius (ACR) has emerged as a widely used metr…
DAGER: Exact Gradient Inversion for Large Language Models
Ivo Petrov, Dimitar I. Dimitrov, Maximilian Baader +2
Federated learning works by aggregating locally computed gradients from multiple clients, thus enabling collaborative training without sharing private client data. However, prior w…
Mitigating Catastrophic Forgetting in Language Transfer via Model Merging
Anton Alexandrov, Veselin Raychev, Mark Niklas Müller +3
As open-weight large language models (LLMs) achieve ever more impressive performances across a wide range of tasks in English, practitioners aim to adapt these models to different…