@article{cascadingadversarialbiasfrominjectionto, title = {Cascading Adversarial Bias from Injection to Distillation in Language Models}, author = {Harsh Chaudhari and Jamie Hayes and Matthew Jagielski and Ilia Shumailov and Milad Nasr and Alina Oprea}, year = {2025}, eprint = {2505.24842}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2505.24842v1}, }