TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport

Summary

TraceRouter++ is a safety intervention framework for large foundation models that traces causal routing pathways activated by harmful inputs and realigns their unsafe activations. It locates a sensitive onset layer via attention divergence, maps sparse autoencoder features to downstream circuits through feature influence scores, and applies a constrained optimal transport soft realignment. The authors report improved adversarial robustness across LLMs, MLLMs and diffusion models with a favorable safety-utility trade-off over evaluated baselines.

Related items

• MediumResearchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak ToolkitSimilar attack · The Hacker News
• InfoAddition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoSafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM ServingSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online
• MediumFree the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak BundlesSimilar attack · Check Point Research