Exact certification of data-poisoning attacks using mixed-integer programming

DOI10.1007/978-3-032-27242-3_32MaRDI QIDQ7356189zbMATH OpenFDO

Authors Philip Sosnin, Jodie Knapp, Fraser Kennedy, Josh Collyer, Calvin Tsay

Publication date 23 September 2026

Full work available at URL https://doi.org/10.1007/978-3-032-27242-3_32

Mathematics Subject Classification ID

Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Mixed integer programming (90C11)

Cites work

• Deep neural networks and mixed integer linear optimization
• Formal verification of piece-wise linear feed-forward neural networks
• Least angle regression. (With discussion)
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Strong mixed-integer programming formulations for trained neural networks
• Three enhancements for optimization-based bound tightening

This page was built for publication: Exact certification of data-poisoning attacks using mixed-integer programming

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7356189)