Stephan Günnemann, Debarghya Ghoshdastidar, Lukas Gosch, Mahalakshmi Sabanayagam
We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| copy not recorded | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| configure_hardware | Ran | this paper's copy was not recorded; identical code first harvested from saper0/qpcert pointer only · get_code("b4c5f4e799dfd30f") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 interest in certifying (i.e., proving) that such changes up to a certain magnitude do not affect test predictions. We, for the first time, certify Graph Neural Networks (GNNs) against poisoning attacks, including backdoors, targeting the node features of a given graph. Our certificates are white-box and based upon (i) the neural tangent kernel, which characterizes the training dynamics of sufficiently wide networks; and (ii) a novel reformulation of the bilevel optimization problem describing poisoning as a mixed-integer linear program. Consequently, we leverage our framework to provide fundamental insights into the role of graph structure and its connectivity on the worst-case robustness behavior of convolution-based and PageRankbased GNNs. We note that our framework is more general and constitutes the first approach to derive white-box poisoning certificates for NNs, which can be of independent interest beyond graph-related tasks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2407.10867")
get_code_for_paper("2407.10867")
have("2407.10867")
Connect an agent — have() is free.