About us

Consortium

Team

Meet the Alumni

Flanders AI

Contact

<h5>Description:</h5>
<p>We provide a closed-form recursive procedure to recover data from gradients in deep neural networks. We name it Recursive Gradient Attack on Privacy (R-GAP)</p>

<h5>More Information:</h5>
<ul>
<li><strong>Grand Challenge/Workpackage(s)</strong>:&nbsp; <a href="/en/research/research-challenges-2019-2023/ai-driven-data-science"[entry:airesearch:58:/research/research-challenges/ai-driven-data-science]data-entry-id="58" target="_blank" rel="noopener">GC1</a> - WP5</li>
<li><strong>Responsible Research Lead</strong>: <a href="mailto:matthew.blaschko@esat.kuleuven.be" target="_blank" rel="noopener">Matthew Blaschko</a></li>
<li><strong>Authors</strong>: <a href="mailto:Junyi.zhu@esat.kuleuven.be" target="_blank" rel="noopener">Junyi Zhu</a>&nbsp;</li>
<li><strong>Programming Language</strong>: Python</li>
<li><a href="https://github.com/JunyiZhu-AI/R-GAP" target="_blank" rel="noopener">Link to the repository</a></li>
<li><strong>Categories</strong>: Images, Networks and graphs&nbsp;</li>
</ul>

<h5>Publications:</h5>
<ul>
<li>J. Zhu,&nbsp; M. Blaschko, "<a href="https://arxiv.org/abs/2010.07733" target="_blank" rel="noopener">R-GAP: Recursive Gradient Attack on Privacy</a>", in Proceedings of the International Conference on Learning Representations, 2021.</li>
</ul>