arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.12679cs.CR
收藏

为何神经结构混淆无法彻底消灭白盒水印

Why Neural Structural Obfuscation Can't Kill White-Box Watermarks for Good!

University of Technology Sydney(悉尼科技大学);CSIRO Data61(澳大利亚联邦科学与工业研究组织数据61);Tsinghua University(清华大学)

Yanna Jiang, Guangsheng Yu, Qingyuan Yu, Yi Chen, Qin Wang

AI总结:

本文重新审视神经结构混淆技术,提出Canon框架可完全恢复其破坏,通过全局规范化恢复网络结构,实现水印验证与任务功能的双重保障。

摘要:

神经结构混淆(NSO)(USENIX Security'23)是一组「零成本」结构编辑变换(nso_zero,nso_clique,nso_split),通过注入虚拟神经元,在保持功能等价性的同时,对网络结构和参数进行根本性修改,从而破坏白盒水印验证。我们重新审视NSO并首次完全恢复其造成的损害。我们将NSO重新定义为图一致性威胁模型,基于生产者-消费者范式,任何生产者节点的混淆都要求所有下游消费者进行兼容的布局更新以维持结构完整性。基于这些信号传播的一致性约束,我们提出了Canon恢复框架,通过探测受攻击模型来识别冗余/虚拟通道,然后通过重构所有下游消费者进行全局规范化,同步fan-out、add和cat等布局。大量实验表明,即使在强组合和扩展NSO攻击下,Canon也实现100%的恢复成功率,恢复水印可验证性同时保持任务实用性。我们的代码可在https://anonymous.4open.science/r/anti-NSO-9874获取。

英文摘要:

Neural Structural Obfuscation (NSO) (USENIX Security'23) is a family of ``zero cost'' structure-editing transforms (\texttt{nso\_zero}, \texttt{nso\_clique}, \texttt{nso\_split}) that inject dummy neurons. By combining neuron permutation and parameter scaling, NSO makes a radical modification to the network structure and parameters while strictly preserving functional equivalence, thereby disrupting white-box watermark verification. This capability has been a fundamental challenge to the reliability of existing white-box watermarking schemes. We rethink NSO and, for the first time, fully recover from the damage it has caused. We redefine NSO as a graph-consistent threat model within a \textit{producer--consumer} paradigm. This formulation posits that any obfuscation of a producer node necessitates a compatible layout update in all downstream consumers to maintain structural integrity. Building on these consistency constraints on signal propagation, we present \textsc{Canon}, a recovery framework that probes the attacked model to identify redundancy/dummy channels and then \textit{globally} canonicalizes the network by rewriting \textit{all} downstream consumers by construction, synchronizing layouts across \texttt{fan-out}, \texttt{add}, and \texttt{cat}. Extensive experiments demonstrate that, even under strong composed and extended NSO attacks, \textsc{Canon} achieves \textbf{100\%} recovery success, restoring watermark verifiability while preserving task utility. Our code is available at https://anonymous.4open.science/r/anti-NSO-9874.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑