@article{adversarialactivationpatchingaframework, title = {Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers}, author = {Santhosh Kumar Ravindran}, year = {2025}, eprint = {2507.09406}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2507.09406v1}, }