@inproceedings{li-etal-2026-evaluating, title = "Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders", author = "Li, Aaron J. and Srinivas, Suraj and Bhalla, Usha and Lakkaraju, Himabindu", editor = "Demberg, Vera and Inui, Kentaro and Marquez, Llu{\'i}s", booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)", month = mar, year = "2026", address = "Rabat, Morocco", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/ingest-eacl/2026.eacl-long.279/", pages = "5940--5957", ISBN = "979-8-89176-380-7" }