Protecting Floating-Point Computation for DNN Binaries with MBA Obfuscation
2026-07-20 • Cryptography and Security
Cryptography and Security
AI summaryⓘ
The authors created FLOB, a method to protect deep learning models saved as programs from being copied or understood by hackers. Normal protection tools don’t work well for these models because they mainly use floating-point math, which is different from regular computer programs. FLOB hides the important math operations by changing how numbers are represented internally without messing up the results. Tests show FLOB is better at stopping reverse engineering while keeping the model’s calculations correct.
deep neural networkscode obfuscationfloating-point computationMixed Boolean-Arithmetic (MBA)reverse engineeringbinary protectionnumerical erroroperator recovery rate
Authors
Yikun Hu, Zichen Zhao, Peixiang Qin, Ziyi Zhou, Jiaping Gui, Yuandao Cai, Wensheng Tang
Abstract
Deep neural networks (DNNs) have become a foundational component of modern computing systems with a wide range of applications, such as computer vision, edge intelligence, etc. For the sake of low latency and data privacy, DNN models are increasingly compiled into executables and deployed on local devices. However, that exposes the models to model theft, enabling adversaries to recover proprietary assets via reverse engineering techniques. While code obfuscation naturally emerges for protecting executables from reverse engineering, existing schemes are primarily designed for traditional programs, focusing on complex control flow structures and integer-based operations. They are fundamentally inappropriate for DNN binaries, which exhibit relatively simple code structures and heavily rely on floating-point computation. In this paper, we propose FLOB, an obfuscation framework that protects floating-point computations in DNN binaries using Mixed Boolean-Arithmetic (MBA) transformations. Our approach lifts floating-point values into a higher-precision binary expansion space and performs MBA transformations at the representation level. The computation is carried out entirely in the lifted space, and the final result is then projected back to the target precision, yielding outputs that are semantically equivalent under the original floating-point format, without introducing additional rounding error. The experimental results show that FLOB outperforms the state-of-the-art obfuscation schemes against existing reverse engineering analyzers and deobfuscators, while preserving computational correctness without introducing additional numerical error, allowing flexible trade-off between protection and performance. Specifically, FLOB reduces the operator recovery rate to 4.51% on average, achieving a 32.82 percentage-point reduction compared to existing methods.