View PDF

Abstract:Pseudorandom error-correcting codes (PRCs), a novel cryptographic primitive recently proposed at CRYPTO 2024, are primarily applied in undetectable watermarking schemes for large generative this http URL, the security of PRCs has not yet been systematically analyzed. To fill this gap, we present the first cryptanalysis of this http URL, focusing on LDPC-PRC, the only known practical instantiation of PRCs, we propose three novel attacks that challenge its undetectability and this http URL rigorously demonstrate the practical threat, we analyze the concrete attack complexity under realistic parameters and validate the attack effectiveness on both real-world large language models and generative image models, including DeepSeek and Stable this http URL analysis shows that the claimed security guarantees of LDPC-PRC are undermined across all practically feasible regimes. For example, our attacks can detect the presence of a watermark with overwhelming probability at a cost of $2^{22}$ this http URL attacks, we further propose three defenses: parameter recommendation, implementation suggestion, and a revised key generation this http URL, PRC-based watermarking schemes still fail to achieve 128-bit security due to inherent constraints of large generative models, such as the maximum output length of large language this http URL, our work clarifies the concrete security limits of PRCs in real-world watermarking applications.

Submission history

From: Tianrui Wang [view email]
[v1] Fri, 19 Dec 2025 07:48:04 UTC (3,749 KB)
[v2] Mon, 15 Jun 2026 02:06:25 UTC (1,385 KB)