AI × CryptoBullisharXiv – CS AI · Mar 56/10
🤖Researchers introduce ZKFL-PQ, a quantum-resistant cryptographic protocol for federated learning in medical AI that combines zero-knowledge proofs, lattice-based encryption, and homomorphic encryption. The protocol achieves 100% rejection of malicious updates while maintaining model accuracy, addressing vulnerabilities from gradient inversion attacks and future quantum threats.
AI × CryptoBullishHugging Face Blog · Aug 27/106
🤖The article discusses the development of encrypted large language models using Fully Homomorphic Encryption (FHE) technology. This approach would allow AI models to process data while keeping it encrypted, potentially addressing privacy concerns in AI applications.
AINeutralarXiv – CS AI · May 276/10
🧠Researchers introduce an anonymous gradient-boosted decision tree (GBDT) protocol enabling secure training on vertically partitioned data between two parties while hiding record identifiers. The approach uses dual circuit-PSI and oblivious pseudorandom functions to eliminate ID exposure risks inherent in standard private set intersection methods, while achieving computational efficiency comparable to non-private approaches.
AIBullishBankless · Feb 276/107
🧠Small AI models are emerging as a potential solution for private AI applications while fully homomorphic encryption remains years away from frontier-scale deployment. The threshold for what constitutes 'good enough' privacy-preserving AI has been lowered, making smaller models more viable for practical use cases.
AI × CryptoBullishHugging Face Blog · Nov 176/107
🤖The article discusses techniques for performing sentiment analysis on encrypted data using homomorphic encryption. This approach allows analysis of sensitive data while maintaining privacy, potentially enabling new applications in finance and other sectors requiring data confidentiality.
CryptoBullishEthereum Foundation Blog · Feb 86/103
⛓️The article discusses recent cryptographic advances including fully homomorphic encryption, which allows computation on encrypted data without decryption. This technology could significantly advance decentralized autonomous organizations by enabling secure, private computation on blockchain networks.
AI × CryptoNeutralVitalik Buterin Blog · Jul 201/102
🤖The article title suggests coverage of Fully Homomorphic Encryption (FHE), a cryptographic technique that allows computations on encrypted data without decryption. However, no article body content was provided for analysis.
