@article{mechanisticinterpretabilityofllmjailbrea, title = {Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs}, author = {Anupam Wagle and Ifrat Ikhtear Uddin and Chaowei Zhang and Longwei Wang}, year = {2026}, eprint = {2607.07903}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2607.07903}, }