Genetic Improvement for DNN Security

Created by W.Langdon from gp-bibliography.bib Revision:1.7644

@InProceedings{Baxter:2024:GI,

• author = "Hunter Baxter and Yu Huang and Kevin Leach",
• title = "Genetic Improvement for {DNN} Security",
• booktitle = "13th International Workshop on Genetic Improvement @ICSE 2024",
• year = "2024",
• editor = "Gabin An and Aymeric Blot and Vesna Nowack and Oliver Krauss and and and Justyna Petke",
• address = "Lisbon",
• month = "16 " # apr,
• publisher = "ACM",
• note = "Best Presentation",
• keywords = "genetic algorithms, genetic programming, Genetic Improvement, Computer Security, ANN",
• isbn13 = "979-8-4007-0573-1/24/04",
• URL = "http://gpbib.cs.ucl.ac.uk/gi2024/Genetic_Improvement_for_DNN_Security.pdf",
• DOI = "doi:10.1145/3643692.3648261",
• slides_url = "http://gpbib.cs.ucl.ac.uk/gi2024/gi_2024_slides/leach-gi24.pdf",
• video_url = "https://www.youtube.com/watch?v=OXiFldz3b1U",
• size = "2 pages",
• abstract = "Genetic improvement (GI) in Deep Neural Networks (DNNs) has traditionally enhanced neural architecture and trained DNN parameters. Recently, GI has supported large language models by optimising DNN operator scheduling on accelerator clusters. However, with the rise of adversarial AI, particularly model extraction attacks, there is an unexplored potential for GI in fortifying Machine Learning as a Service (MLaaS) models. We suggest a novel application of GI, not to improve model performance, but to diversify operator parallelism for the purpose of a moving target defence against model extraction attacks. We discuss an application of GI to create a DNN model defense strategy that uses probabilistic isolation, offering unique benefits not present in current DNN defense systems.",
• notes = "GI @ ICSE 2024, part of \cite{an:2024:GI}",

}

Genetic Programming entries for Hunter Baxter Yu Huang Kevin Leach

Citations