no code implementations • 29 Feb 2024 • Nikola Jovanović, Robin Staab, Martin Vechev
LLM watermarking has attracted attention as a promising way to detect AI-generated content, with some works suggesting that current schemes may already be fit for deployment.
1 code implementation • 17 Nov 2023 • Robin Staab, Nikola Jovanović, Mislav Balunović, Martin Vechev
We propose a novel vertical DM (vDM) workflow based on data generalization, which by design ensures that no full-resolution client data is collected during training and deployment of models, benefiting client privacy by reducing the attack surface in case of a breach.
1 code implementation • 5 Jun 2023 • Kostadin Garov, Dimitar I. Dimitrov, Nikola Jovanović, Martin Vechev
Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private.
1 code implementation • 27 Oct 2022 • Nikola Jovanović, Marc Fischer, Samuel Steffen, Martin Vechev
We employ these building blocks to enable privacy-preserving NN inference with robustness and fairness guarantees in a system called Phoenix.
1 code implementation • 13 Oct 2022 • Nikola Jovanović, Mislav Balunović, Dimitar I. Dimitrov, Martin Vechev
To produce a practical certificate, we develop and apply a statistical procedure that computes a finite sample high-confidence upper bound on the unfairness of any downstream classifier trained on FARE embeddings.
2 code implementations • 17 Feb 2022 • Mislav Balunović, Dimitar I. Dimitrov, Nikola Jovanović, Martin Vechev
Recent work shows that sensitive user data can be reconstructed from gradient updates, breaking the key privacy promise of federated learning.
no code implementations • 25 Feb 2021 • Nikola Jovanović, Zhao Meng, Lukas Faber, Roger Wattenhofer
We study the problem of adversarially robust self-supervised learning on graphs.
no code implementations • 12 Feb 2021 • Nikola Jovanović, Mislav Balunović, Maximilian Baader, Martin Vechev
Certified defenses based on convex relaxations are an established technique for training provably robust models.
1 code implementation • 3 Nov 2018 • Cătălina Cangea, Petar Veličković, Nikola Jovanović, Thomas Kipf, Pietro Liò
Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks.