Seed Hijacking of LLM Sampling and Quantum Random Number Defense

📅 2026-05-08
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work identifies a critical security vulnerability in the autoregressive sampling process of large language models (LLMs), which relies on deterministic pseudorandom number generators (PRNGs) and is thus susceptible to supply chain attacks. The authors introduce SeedHijack, the first backdoor attack that precisely injects target tokens by manipulating the PRNG seed without altering the model itself. The attack achieves a 99.6% success rate on GPT-2 and 100% success across multiple aligned models ranging from 1.5B to 7B parameters. To counter this threat, the paper proposes a practical defense mechanism leveraging a quantum random number generator (QRNG), which incurs only a 0.6% latency overhead and 7.7 MB of additional memory while effectively neutralizing such attacks.
📝 Abstract
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. In a 540-trial benchmark on GPT-2 (124M), the attack achieves 99.6% exact token injection across 9 sampling configurations; it reaches 100% success on four aligned models (1.5B-7B, RLHF/SFT/reasoning distillation) and bypasses all alignment methods tested in this work. We further propose a defense based on a hardware quantum random number generator (QRNG), which neutralizes the attack in our evaluated threat model with negligible median overhead (+0.6% latency, +7.7 MB memory). Our work identifies a critical sampling-layer vulnerability and provides a practical, deployable QRNG-based defense.
Problem

Research questions and friction points this paper is trying to address.

LLM sampling
PRNG vulnerability
supply-chain attack
token injection
backdoor attack
Innovation

Methods, ideas, or system contributions that make the work stand out.

SeedHijack
PRNG backdoor
quantum random number generator
LLM sampling vulnerability
hardware-based defense
🔎 Similar Papers
2024-10-02arXiv.orgCitations: 1
Z
Ziyang You
School of Electronic, Electrical and Physics, Fujian University of Technology, Fuzhou 350118, China
X
Xiaoke Yang
School of Humanities, Fujian University of Technology, Fuzhou 350118, China
Z
Zhanling Fan
Department of Investigation, Fujian Police College, Fuzhou 350007, China
F
Feng Guo
School of Electronic, Electrical and Physics, Fujian University of Technology, Fuzhou 350118, China
X
Xiaogen Zhou
School of Electronic, Electrical and Physics, Fujian University of Technology, Fuzhou 350118, China
X
Xuxing Lu
School of Electronic, Electrical and Physics, Fujian University of Technology, Fuzhou 350118, China