Research
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
Publication date not yet evaluated · Added arxiv.org
Page published
Coverage timeline
Single-source research — one report is available.
Why it matters
Understanding how adversarial prompts reroute an LLM's internal computation to suppress safety components gives defenders a principled, causal basis for diagnosing and hardening models against jailbreaks rather than relying only on input-output patches.
Researchers from the University of South Dakota and Yangzhou University introduce a mechanistic interpretability framework that diagnoses LLM jailbreaks and adversarial prompts by constructing and aligning internal computation (attribution) graphs for clean versus attacked prompts. The method decomposes internal reasoning into invariant, suppressed, and emergent structures, identifies recurring vulnerability motifs, and performs causal interventions that improve robustness across multiple open-source LLMs and jailbreak benchmarks.