TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport

Summary

TraceRouter++ is a routing-level safety framework for large foundation models that traces causal routing pathways activated by harmful inputs and realigns their unsafe activation states. It uses sparse autoencoders, feature influence scores, and a constrained optimal transport soft realignment instead of rigid neuron suppression. The authors report improved adversarial robustness and a favorable safety-utility trade-off across LLMs, MLLMs, and diffusion models.

Related items

• MediumResearchers Uncover Prompt Adware Hidden in OpenAI Codex Jailbreak ToolkitSimilar attack · The Hacker News
• 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
• InfoCrowdStrike to Acquire Dreadnode to Bring Automated AI Security Testing to the Falcon PlatformSimilar attack · CrowdStrike Blog
• InfoPGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language ModelsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)