# VPN: Verification of Poisoning in Neural Networks Source: [VPN: Verification of Poisoning in Neural Networks]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:11:46.889Z Authors: Youcheng Sun, Muhammad Usman, Divya Gopinath, Corina S. P\\u{a}s\\u{a}reanu Published: 2022-05-08T15:16:05.000Z ## Abstract Neural networks are successfully used in a variety of applications, many of them having safety and security concerns. As a result researchers have proposed formal verification techniques for verifying neural network properties. While previous efforts have mainly focused on checking local robustness in neural networks, we instead study another neural network security issue, namely data poisoning. In this case an attacker inserts a trigger into a subset of the training data, in such a way that at test time, this trigger in an input causes the trained model to misclassify to some target class. We show how to formulate the check for data poisoning as a property that can be checked with off-the-shelf verification tools, such as Marabou and nneum, where counterexamples of failed checks constitute the triggers. We further show that the discovered triggers are \`transferable' from a small model to a larger, better-trained model, allowing us to analyze state-of-the art performant models trained for image classification tasks. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()