ReCast: Contract-Preserving Protection for Fixed-Interface Multimodal Reasoning

arXiv:2610.01184 · cs.CR, cs.AI, cs.CL · Submitted 2026-10-01 · Read on arXiv

cs.CR, cs.AI, cs.CL

Submitted: 2026-10-01

Updated: 2026-10-01

Comments: 24 pages, 10 figures

Code: https://github.com/deepseek-ai/deepseek-harness

License: http://creativecommons.org/licenses/by/4.0/

The gist: Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content.

Terminology

Abstract

Remote multimodal models offer strong numerical reasoning capabilities over charts and speech, but sending private inputs risks exposing sensitive content. Text-only sanitization cannot directly satisfy fixed media interfaces, while identity anonymization leaves the underlying task content exposed. We introduce ReCast, an agentic plug-in framework that replaces source-specific content while preserving task-relevant relations and the required input modality. ReCast locally converts inputs into a shared textual evidence-query record, jointly rewrites entities and topics with a distilled 4B model, and substitutes values through a locally invertible, role-aware numerical map. A reconstruction agent generates and validates the required media from the protected record. The remote solver returns a program whose protected operands are restored locally before execution. On 4,000 held-out ChartQA and NMSQA examples, ReCast achieves 75.10% accuracy, retaining 92.43% of unprotected remote accuracy, while a model-based audit flags source-content leakage in 7.95% of solver-bound requests. It outperforms all evaluated local baselines, preserving the benefit of remote reasoning while reducing source-content exposure under existing media interfaces.

Sources

Related papers