Protecting Floating-Point Computation for DNN Binaries with MBA Obfuscation

arXiv:2607.17603 · cs.CR · Submitted 2026-07-20 · Read on arXiv

Yikun Hu, Zichen Zhao, Peixiang Qin, Ziyi Zhou, Jiaping Gui, Yuandao Cai, Wensheng Tang

cs.CR

Submitted: 2026-07-20

Comments: This submission was made prematurely. The authors withdraw it to substantially revise the manuscript before further dissemination

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Alignment — 2× in this paper · explained in 1 episode
• Analyzer — 2× in this paper · explained in 1 episode
• Communication Overhead — 1× in this paper · explained in 2 episodes
• Core — 1× in this paper · explained in 2 episodes
• Edge Devices — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• SMT solver — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Glow: Graph Lowering Compiler Techniques for Neural Networks

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs