[1]
Pathmanathan, P. et al. 2026. AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 44 (Mar. 2026), 37820–37829. DOI:https://doi.org/10.1609/aaai.v40i44.41118.