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

Neural Structural Obfuscation (NSO) (USENIX Security’23) is a family of ``zero cost’’ structure-editing transforms ($\mathtt{\text{nso\_zero}}$, $\mathtt{\text{nso\_clique}}$, $\mathtt{\text{nso\_split}}$) 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 $\mathit{\text{producer–consumer}}$ 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 $\text{textsc}Canon$, a recovery framework that probes the attacked model to identify redundancy/dummy channels and then $\mathit{\text{globally}}$ canonicalizes the network by rewriting $\mathit{\text{all}}$ downstream consumers by construction, synchronizing layouts across $\mathtt{\text{fan-out}}$, $\mathtt{\text{add}}$, and $\mathtt{\text{cat}}$. Extensive experiments demonstrate that, even under strong composed and extended NSO attacks, $\text{textsc}Canon$ achieves $\mathbf{\text{100\%}}$ recovery success, restoring watermark verifiability while preserving task utility. Our code is available at https://anonymous.4open.science/r/anti-NSO-9874.