DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense
This exposes a previously overlooked supply-chain vulnerability in generative AI systems, offering a hardware-level mitigation for security-critical applications.
DiffusionHijack is a supply-chain backdoor attack that hijacks PRNGs in diffusion models to force deterministic, attacker-controlled image generation (SSIM=1.00) without modifying model weights, and is undetectable by existing defenses. A quantum random number generator (QRNG) countermeasure completely neutralizes the attack, reducing output similarity to random baseline levels (SSIM<0.20 for SD 1.x, <0.45 for SDXL).
Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor attack that hijacks the PRNG to deterministically control generated images. A malicious PRNG, injected via compromised packages, forces pixel-perfect reproduction of attacker-chosen content (SSIM = 1.00, N = 100 trials) on Stable Diffusion v1.4, v1.5, and SDXL -- without modifying model weights. The attack is inherently undetectable by existing model auditing and content moderation mechanisms, as it operates entirely outside the neural network computation graph. The attack remains effective under stochastic sampling (eta > 0), bypasses CLIP-based safety checkers (98-100% success), and operates independently of the user's prompt. As a countermeasure, we replace the PRNG with a quantum random number generator (QRNG), which provides information-theoretic unpredictability. Across N = 100 prompt-model combinations, QRNG defense completely neutralizes the attack, reducing output similarity to random baseline levels (SSIM < 0.20 for SD 1.x models, < 0.45 for SDXL). This work exposes a previously overlooked supply-chain vulnerability and offers a hardware-level fundamental mitigation for generative AI systems.