Seed Hijacking of LLM Sampling and Quantum Random Number Defense

ArXi:2605.08313v1 Announce Type: cross Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chain attack surface overlooked by existing defenses. We present SeedHijack, a backdoor attack that manipulates PRNG outputs to force attacker-specified token selection without altering model logits.