Pathmanathan, P., Sehwag, U. M., Panaitescu-Liess, M.-A., Chiang, C.-Y. J., & Huang, F. (2026). AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment. Proceedings of the AAAI Conference on Artificial Intelligence, 40(44), 37820–37829. https://doi.org/10.1609/aaai.v40i44.41118