Preprint
Jul 2026
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
Large language models (LLMs) exhibit remarkable capabilities but remain highly vulnerable to adversarial prompts and jailbreak attacks. Existing approaches primarily analyze these failures through input-output behaviors or attribution methods, offering limited insight into how adversarial perturbations alter the model'...
Anupam Wagle, Ifrat Ikhtear Uddin, Chaowei Zhang et al.
· 1 citation