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 • 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 • 14 Feb 2024 • Jingxuan He, Mark Vero, Gabriela Krasnopolska, Martin Vechev
However, existing instruction tuning schemes overlook a crucial aspect: the security of generated code.
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.
no code implementations • 7 Jul 2023 • Mark Vero, Mislav Balunović, Martin Vechev
To ensure high synthetic data quality in the presence of custom specifications, CuTS is pre-trained on the original dataset and fine-tuned on a differentiable loss automatically derived from the provided specifications using novel relaxations.
1 code implementation • 4 Oct 2022 • Mark Vero, Mislav Balunović, Dimitar I. Dimitrov, Martin Vechev
A successful attack for tabular data must address two key challenges unique to the domain: (i) obtaining a solution to a high-variance mixed discrete-continuous optimization problem, and (ii) enabling human assessment of the reconstruction as unlike for image and text data, direct human inspection is not possible.
no code implementations • 29 Apr 2022 • Thorir Mar Ingolfsson, Mark Vero, Xiaying Wang, Lorenzo Lamberti, Luca Benini, Matteo Spallanzani
The computational demands of neural architecture search (NAS) algorithms are usually directly proportional to the size of their target search spaces.