ObfusX: Routing obfuscation with explanatory analysis of a machine learning attack
ObfusX: Routing obfuscation with explanatory analysis of a machine learning attack
复制标题
ObfusX：通过机器学习攻击的解释性分析进行路由混淆
DOI：
10.1016/j.vlsi.2022.10.013
复制
发表时间：
2023
期刊：
影响因子：
1.9
通讯作者：
Topaloglu, Rasit Onur
中科院分区：
文献类型：
--
作者：
Zeng, Wei;Davoodi, Azadeh;Topaloglu, Rasit Onur
这是第一个结合机器学习 (ML)“可解释性”方面最新进展来构建名为 ObfusX 的路由混淆器的作品。我们采用了最新的指标——SHAP值——它解释了每个布局特征可以在多大程度上揭示最近基于机器学习的分割制造攻击模型的每个未知连接。基于 SHAP 的分析的独特优势包括能够识别最佳的混淆候选者，以及使它们容易受到攻击的主要布局特征。因此，与之前的工作相比，ObfusX 在使用过孔扰动方案进行混淆时可以实现更好的命中率（降低 97%），同时扰动明显更少的网络。当使用线提升方案施加相同的线长度限制时，ObfusX 在性能指标上表现明显更好（例如，网表恢复百分比平均减少 2.4 倍）。
This is the first work that incorporates recent advancements in "explainability" of machine learning (ML) to build a routing obfuscator called ObfusX. We adopt a recent metric---the SHAP value---which explains to what extent each layout feature can reveal each unknown connection for a recent ML-based split manufacturing attack model. The unique benefits of SHAP-based analysis include the ability to identify the best candidates for obfuscation, together with the dominant layout features which make them vulnerable. As a result, ObfusX can achieve better hit rate (97% lower) while perturbing significantly fewer nets when obfuscating using a via perturbation scheme, compared to prior work. When imposing the same wirelength limit using a wire lifting scheme, ObfusX performs significantly better in performance metrics (e.g., 2.4 times more reduction on average in percentage of netlist recovery).