Kyung Hee University

Nanoparticle neurological safety is hard to predict from material properties alone, because exposure conditions, disease context and host responses reshape outcomes. Across 893 experimental contexts from 599 neurological studies, pro-inflammatory, anti-inflammatory/resolution and apoptosis-associated responses were harmonized into a Conserved Response Axis and added layer by layer to material descriptors. With a Random Forest model, biosafety ROC-AUC rose from 0.66 with material properties alone to 0.88 with exposure and biological context and 0.90 with cellular responses; recovery rose from 0.64 to 0.77 and 0.78.

Nanoparticle neurological safety is hard to predict from material properties alone, because exposure conditions, disease context and host responses reshape outcomes. Across 893 experimental contexts from 599 neurological studies, pro-inflammatory, anti-inflammatory/resolution and apoptosis-associated responses were harmonized into a Conserved Response Axis and added layer by layer to material descriptors. With a Random Forest model, biosafety ROC-AUC rose from 0.66 with material properties alone to 0.88 with exposure and biological context and 0.90 with cellular responses; recovery rose from 0.64 to 0.77 and 0.78.

LADE extracts model-agnostic latent safety signals from dark knowledge in the first-token output probability distribution by contrasting harmful and benign queries, maps the selected tokens across tokenizers, and filters harmful queries via kNN distance before generation; across Llama-2-7B-Chat, Llama-3-8B-Instruct, Qwen2-7B-Instruct, Qwen3-8B, Gemma-7B-it, and Mistral-7B-Instruct-v0.3, it attains the lowest or near-lowest average compliance under multiple jailbreak attacks and the best safety-utility average on six of eight models.

LADE extracts model-agnostic latent safety signals from dark knowledge in the first-token output probability distribution by contrasting harmful and benign queries, maps the selected tokens across tokenizers, and filters harmful queries via kNN distance before generation; across Llama-2-7B-Chat, Llama-3-8B-Instruct, Qwen2-7B-Instruct, Qwen3-8B, Gemma-7B-it, and Mistral-7B-Instruct-v0.3, it attains the lowest or near-lowest average compliance under multiple jailbreak attacks and the best safety-utility average on six of eight models.