Lukas Gosch

me.png

Hello, welcome to my corner of the web!

I am a researcher focusing on topics at the intersection of machine learning and optimization. I am doing my PhD at TU Munich under the supervision of Prof. Günnemann in the DAML research group and am part of the relAI graduate school. Currently, I am especially interested in the use of machine learning for and in optimization problems commonly arising e.g., in operations research. Before this, I have worked extensively on robustness verification, graph neural networks, and general robustness topics.

If you want to contact me, best write me an e-mail: lukas . gosch [at] tum.de. Scroll down to find my other social media appearances.

Quick Link: Resume/CV

news

Feb 1, 2025 Our paper Exact Certification of (Graph) Neural Networks Against Label Poisoning got accepted to ICLR 2025 (Spotlight, top 5.1%) :tada:.
Dec 1, 2024 Our paper Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks won the best paper award at AdvML-Frontiers@NeurIPS 2024 :tada:.
Nov 15, 2024 I visited and gave an invited talk in the group of Prof. Martin Vechev at INSAIT. It was an amazing visit, thanks to Prof. Martin Vechev and his institute for inviting and hosting me!
Nov 1, 2024 Our paper Assessing Robustness via Score-Based Adversarial Image Generation got accepted to TMLR :tada:.
Jul 1, 2024 Our paper Relaxing Graph Transformers for Adversarial Attacks got accepted at Differentiable Almost Everything@ICML 2024 :tada:.
Oct 1, 2023 Our paper Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions got accepted at NeurIPS 2023 :tada:.
Jun 1, 2023 Our paper Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness got accepted at AdvML Frontiers@ICML2023 :tada:.
Feb 1, 2023 Our paper Revisiting Robustness in Graph Machine Learning got accepted at ICLR 2023 :tada:.

selected publications

  1. Exact Certification of (Graph) Neural Networks Against Label Poisoning
    Mahalakshmi Sabanayagam*, Lukas Gosch*, Stephan Günnemann, and 1 more author
    In The Thirteenth International Conference on Learning Representations (ICLR), Spotlight, 2025
  2. Provable robustness of (graph) neural networks against data poisoning and backdoor attacks
    Lukas Gosch*, Mahalakshmi Sabanayagam*, Debarghya Ghoshdastidar, and 1 more author
    NeurIPS 2024’ AdvML-Frontiers Workshop (Best Paper Award), 2024
  3. Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
    Lukas Gosch, Simon Geisler, Daniel Sturm, and 3 more authors
    In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023
  4. Revisiting Robustness in Graph Machine Learning
    Lukas Gosch, Daniel Sturm, Simon Geisler, and 1 more author
    In The Eleventh International Conference on Learning Representations (ICLR), 2023