AI-Enhanced Zero-Knowledge Authentication for High-Mobility IoT Using Predictive Token Learning

Abstract

High-mobility Internet of Things (IoT) for vehicle-to-grid (V2G) demand response (DR), including roaming between charge point operators (CPOs), requires privacy-preserving authentication with sub-1-ms responses and cross-domain scalability as devices exceed <inline-formula> <tex-math notation="LaTeX">$200{\,}\mathrm {km/h}$ </tex-math></inline-formula>. Mechanisms must run on constrained hardware while remaining compatible with EV-charging message flows such as ISO 15118–20 and OCPP 2.0.1. Many deployed schemes reauthenticate from scratch, which inflates computation and airtime; static credentials also ignore trajectory context and struggle with rapid mobility. We present a zero-knowledge proof-based authentication scheme (ZKPAS) for V2G/DR that proves possession without disclosure and replaces heavy handshakes with compact, mobility-aware proofs, targeting latency <inline-formula> <tex-math notation="LaTeX">$L\lt 1{\,}\mathrm {ms}$ </tex-math></inline-formula>. ZKPAS integrates four elements: 1) Schnorr-style zero-knowledge (ZK) proofs over elliptic curves validate identity without exposing trajectory or long-term identifiers; 2) sliding-window tokens bind to DR windows and reduce per-segment communication from <inline-formula> <tex-math notation="LaTeX">$\mathcal {O}(n)$ </tex-math></inline-formula> to <inline-formula> <tex-math notation="LaTeX">$\mathcal {O}(\log n)$ </tex-math></inline-formula>; 3) predictive token generation with long short-term memory (LSTM) models trained on GeoLife and T-Drive precomputes material, yielding 84.7% token reuse along trajectories; and 4) cross-domain authentication employs <inline-formula> <tex-math notation="LaTeX">$(t,n)$ </tex-math></inline-formula>-threshold cryptography for Byzantine-tolerant roaming across operators. We prove resistance to impersonation, replay, man-in-the-middle, and trajectory inference; under the computational Diffie–Hellman problem (CDHP), the adversary’s success probability satisfies <inline-formula> <tex-math notation="LaTeX">$\Pr [\text {break}]\le 2^{-\lambda }$ </tex-math></inline-formula>. On real transportation topologies, ZKPAS cuts computation by 71.8%, authentication latency by 93.9%, and energy by 69.5% while interfacing with V2G/DR control flows. The protocol sustains a 98.5% authentication success rate at <inline-formula> <tex-math notation="LaTeX">$250{\,}\mathrm {km/h}$ </tex-math></inline-formula>.

@article{ahmed2026enhanced,
  title   = {AI-Enhanced Zero-Knowledge Authentication for High-Mobility IoT Using Predictive Token Learning},
  author  = {Ahmed, Shafiq and Anisi, M. H.},
  journal = {IEEE Internet of Things Journal},
  volume  = {13},
  number  = {5},
  pages   = {9068--9077},
  year    = {2026},
  doi     = {10.1109/jiot.2025.3644599}
}