eprint.iacr.orgpaperSecAgg++: A Post-Quantum Privacy Preserving Federated Learning Protocol
SecAgg++ is a masking-based secure aggregation protocol for single-server federated learning that swaps in post-quantum cryptographic primitives. It keeps the communication and computation efficiency of SecAgg and SecAgg+ and handles client dropout through an efficient recovery procedure built on secret sharing and additive masking. It matters because existing masking-based aggregation protocols are not post-quantum secure, so client model updates would be exposed to quantum-capable adversaries.
TL;DR Post-quantum variant of SecAgg/SecAgg+ for privacy-preserving federated learning, with secret-sharing-based dropout recovery.
Also seen from another angle🧠 AI →
Organisations named here
- SecAgg++
Technologies named here
- SecAgg
- SecAgg+
Techniques named here
- Secure aggregation for privacy-preserving federated learning
- Masking-based secure aggregation
- Post-quantum cryptographic primitives
- Secret sharing
- Client dropout recovery procedure
Related in AI Security
blog.talosintelligence.comtoolIntroducing CAIRN: Frontier tracking for AI-integrated malware (Cisco Talos)
github.comadvisoryFlowise MCP Security Bypass Enables RCE
github.comrepoYesWeHack Claude Kit
jfrog.comarticle