{"slug": "certified-but-private-scalable-zero-knowledge-proofs-for-neural-network", "title": "Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees", "summary": "Researchers introduced PANDA, a scalable zero-knowledge proof system built on the CROWN framework, that proves neural network robustness and fairness without revealing private parameters. PANDA generates proofs for networks with over 2.9 million parameters in 5 minutes and verifies them in 10 seconds, supporting networks four orders of magnitude larger than prior approaches with polynomial scaling.", "body_md": "arXiv:2608.17070v1 Announce Type: new\nAbstract: With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly important in safety-critical and legal-compliance settings. However, model parameters are often commercial secrets that cannot be disclosed to auditors or end users. To this end, we present PANDA, a scalable system that uses zero-knowledge proofs (ZKPs) to prove the robustness and fairness properties of a model without revealing its private parameters. PANDA is built on top of CROWN, an efficient robustness certification framework that is used in many state-of-the-art formal verification tools for neural networks. The core contribution of PANDA is a novel algorithm for proving linear relaxation bounds for non-linear activation layers, yielding simple, lightweight proofs. Remarkably, our system can generate proofs of local robustness for neural networks with more than 2.9M parameters in 5 minutes, and can verify them in 10 seconds. Prior ZKP-based robustness system rely on exponential-time algorithms that cannot scale to nontrivial networks. In contrast, PANDA scales polynomially in the number of neurons in a network, allowing us to support neural networks 4 orders of magnitude larger than previous approaches with significantly reduced prover overhead.", "url": "https://wpnews.pro/news/certified-but-private-scalable-zero-knowledge-proofs-for-neural-network", "canonical_source": "https://arxiv.org/abs/2608.17070", "published_at": "2026-08-19 04:00:00+00:00", "updated_at": "2026-08-19 04:13:40.708430+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-research"], "entities": ["PANDA", "CROWN"], "alternates": {"html": "https://wpnews.pro/news/certified-but-private-scalable-zero-knowledge-proofs-for-neural-network", "markdown": "https://wpnews.pro/news/certified-but-private-scalable-zero-knowledge-proofs-for-neural-network.md", "text": "https://wpnews.pro/news/certified-but-private-scalable-zero-knowledge-proofs-for-neural-network.txt", "jsonld": "https://wpnews.pro/news/certified-but-private-scalable-zero-knowledge-proofs-for-neural-network.jsonld"}}