no code implementations • 16 Apr 2024 • Batuhan Tömekçe, Mark Vero, Robin Staab, Martin Vechev
As large language models (LLMs) become ubiquitous in our daily tasks and digital interactions, associated privacy risks are increasingly in focus.
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.
no code implementations • 21 Feb 2024 • Robin Staab, Mark Vero, Mislav Balunović, Martin Vechev
Recent work in privacy research on large language models has shown that they achieve near human-level performance at inferring personal data from real-world online texts.
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 • 11 Oct 2023 • Robin Staab, Mark Vero, Mislav Balunović, Martin Vechev
In this work, we present the first comprehensive study on the capabilities of pretrained LLMs to infer personal attributes from text.
2 code implementations • ICLR 2022 • Mislav Balunović, Dimitar I. Dimitrov, Robin Staab, Martin Vechev
We demonstrate that existing leakage attacks can be seen as approximations of this optimal adversary with different assumptions on the probability distributions of the input data and gradients.
1 code implementation • 14 Oct 2021 • Mark Niklas Müller, Marc Fischer, Robin Staab, Martin Vechev
We present a new abstract interpretation framework for the precise over-approximation of numerical fixpoint iterators.