- author = "Irina Maliukov and Gera Weiss and Oded Margalit and Achiya Elyasaf",
- title = "Evolving Assembly Code in an Adversarial Environment",
- booktitle = "Proceedings of the 2024 Genetic and Evolutionary Computation Conference Companion",
- year = "2024",
- editor = "Dominik Sobania and Aymeric Blot",
- pages = "723--726",
- address = "Melbourne, Australia",
- series = "GECCO '24",
- month = "14-18 " # jul,
- organisation = "SIGEVO",
- publisher = "Association for Computing Machinery",
- publisher_address = "New York, NY, USA",
- keywords = "genetic algorithms, genetic programming, Search-Based Software Engineering, SBSE, assembly, code generation, cyber-security, CodeGuru Xtreme, ANN:poster",
- isbn13 = "979-8-4007-0495-6",
-
URL = "
https://human-competitive.org/sites/default/files/elyasafentry.txt",
-
URL = "
https://human-competitive.org/sites/default/files/elyasafpaper.pdf",
-
URL = "https://arxiv.org/html/2403.19489v1",
-
DOI = "
doi:10.1145/3638530.3654209",
- size = "4 pages",
- size = "9 pages",
- abstract = "we evolve assembly code for the CodeGuru competition. The competition goal is to create a survivor, an assembly program that runs the longest in shared memory, by resisting attacks from adversary survivors and finding their weaknesses. For evolving top-notch solvers, we specify a Backus Normal Form (BNF) for the assembly language and synthesise the code from scratch using Genetic Programming (GP). We evaluate the survivors by running CodeGuru games against human-written winning survivors. Our evolved programs found weaknesses in the programs they were trained against and used them. In addition, we compare our approach with a Large-Language Model, LLM, demonstrating that the latter cannot generate a survivor that can win at any competition. This work has important applications for cyber-security, as we use evolution to detect weaknesses in survivors. The assembly BNF is domain-independent; thus, by modifying the fitness function, it can detect code weaknesses and help fix them. Finally, the CodeGuru competition offers a novel platform for analyzing GP and code evolution in adversarial environments. To support further research in this direction, we provide a thorough qualitative analysis of the evolved survivors and the weaknesses found.",
-
notes = "Entered 2024 HUMIES See \cite{maliukov2024evolving}
also known as \cite{maliukov:2024:GECCOcomp}
GECCO-2024 SBSE A Recombination of the 33rd International Conference on Genetic Algorithms (ICGA) and the 29th Annual Genetic Programming Conference (GP)",
