7 papers · 1 filter
Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning
Ajinkya Mohgaonkar, Lukas Gosch, Mahalakshmi Sabanayagam +2
Label-flipping attacks, which corrupt training labels to induce misclassifications at inference, remain a major threat to supervised learning models. This drives the need for robus…
Exact Certification of (Graph) Neural Networks Against Label Poisoning
Mahalakshmi Sabanayagam, Lukas Gosch, Stephan Günnemann +1
Machine learning models are highly vulnerable to label flipping, i.e., the adversarial modification (poisoning) of training labels to compromise performance. Thus, deriving robustn…
Adversarial Robustness of Graph Transformers
Philipp Foth, Lukas Gosch, Simon Geisler +2
Existing studies have shown that Message-Passing Graph Neural Networks (MPNNs) are highly susceptible to adversarial attacks. In contrast, despite the increasing importance of Grap…
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
Lukas Gosch, Mahalakshmi Sabanayagam, Debarghya Ghoshdastidar +1
Generalization of machine learning models can be severely compromised by data poisoning, where adversarial changes are applied to the training data. This vulnerability has led to i…
Expressivity of Graph Neural Networks Through the Lens of Adversarial Robustness
Francesco Campi, Lukas Gosch, Tom Wollschläger +2
We perform the first adversarial robustness study into Graph Neural Networks (GNNs) that are provably more powerful than traditional Message Passing Neural Networks (MPNNs). In par…
Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
Lukas Gosch, Simon Geisler, Daniel Sturm +3
Despite its success in the image domain, adversarial training did not (yet) stand out as an effective defense for Graph Neural Networks (GNNs) against graph structure perturbations…