| Home > Books and collections > Book chapters > Building Resilient AI : |
| Imprint: | Sydney : IEEE, 2024 |
| Description: | 8 pàg. |
| Abstract: | In many machine learning scenarios, training occurs outside the control of the model sponsor or the entity using the model. A growing concern in such settings revolves around model poisoning and data poisoning-how training is conducted and which data contributes to the process. This paper introduces a protective scheme against model and data poisoning attacks. Leveraging cryptographic primitives such as hashes, signature schemes, and zero-knowledge proofs, the scheme ensures the integrity of the training process. Hashing maintains the continuity of data from authenticated sensors, while signatures validate the data. In the end, zero-knowledge proofs verify the correct model computation by the entity carrying out the training process. By adopting this approach, model sponsors can securely delegate training tasks, guaranteeing the authenticity of the results. Implementation and testing demonstrate the scheme's feasibility, effectively countering data and model poisoning threats. |
| Grants: | Agencia Estatal de Investigación PID2021-125962OB-C33 Agencia Estatal de Investigación PID2021-125962OB-C31 Agència de Gestió d'Ajuts Universitaris i de Recerca 2021/SGR-00643 |
| Note: | Altres ajuts: Plan de Recuperación, Transformación y Resiliencia funded with Next Generation EU funds through the project DANGER INCIBE-C062/23 |
| Rights: | Aquest material està protegit per drets d'autor i/o drets afins. Podeu utilitzar aquest material en funció del que permet la legislació de drets d'autor i drets afins d'aplicació al vostre cas. Per a d'altres usos heu d'obtenir permís del(s) titular(s) de drets. |
| Language: | Anglès |
| Document: | Capítol de llibre ; recerca ; Versió acceptada per publicar |
| Subject: | Federated and outsourced learning ; Verifiable machine learning ; Zero-knowledge proofs |
| Published in: | 2024 17th International Conference on Security of Information and Networks (SIN), 2024, p. 1-8, ISBN 979-8-3315-0973-6 |
Available from: 2027-02-28 Postprint |