BernBRS:面向 DeepBern-Nets 的认证式后向可达集分析框架
BernBRS: Certified Backward Reachability for Deep Bernstein Neural Networks
做神经网络形式化验证的人可以看看这篇。它利用 Bernstein 多项式激活的数学性质做后向可达集分析,连 Half-Cheetah 控制器和 TinyBERT 蒸馏网络这种高维模型都能验证,而现有认证方法在这类规模上基本跑不动。
arXiv 论文提出 BernBRS,一个针对 DeepBern-Nets(使用 Bernstein 多项式激活函数的神经网络)的后向可达集分析框架,可同时计算 Backward Reachable Set 的认证式内近似和外近似。
技术机制上,BernBRS 不依赖单一凸包络,而是通过分析激活模式对输入空间进行覆盖细化,在 relaxation gap 的精确分解预测误差降幅最大的位置切分输入域,实现针对性精化。这使它能够扩展到现有认证方法无法处理的高维大规模架构。
作者在两个高维模型上验证:Half-Cheetah 控制器的线性化闭环近似,以及 Transformer block 蒸馏出的 Bernstein student 网络,并实证分析了模型层面的保证与原始 Half-Cheetah 和 TinyBERT 分类器之间的关系。
BernBRS: Certified Backward Reachability for Deep Bernstein Neural Networks
Ensuring the safety of complex neural network systems requires mathematically rigorous verification. While backward reachability analysis is a critical tool for identifying safe initial states, computing tight, formal bounds remains notoriously difficult to scale. Recent advancements have demonstrated that DeepBern-Nets neural networks utilizing Bernstein polynomial activation functions possess advantageous mathematical properties that enable exceptionally fast and tight forward reachability analysis. Building upon this efficiency, this paper introduces BernBRS, a highly accurate and scalable framework for the backward reachability analysis of DeepBern-Nets. BernBRS simultaneously computes certified inner and outer approximations of the Backward Reachable Set (BRS). Rather than relying on single convex bounding, our method intelligently refines a cover of the input space by analyzing activation patterns, splitting the input domain precisely where an exact decomposition of the relaxation gap predicts the most significant reduction in error. This targeted refinement enables high levels of scalability to highly complex and massive architectures that remain intractable for existing certified methods. We demonstrate the efficacy of our framework on high-dimensional models, including a linearized closed-loop approximation of the Half-Cheetah controller and a distilled Bernstein student of a Transformer block and we empirically study how these model-level guarantees relate to the original Half-Cheetah and TinyBERT classifier, respectively.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include BernBRS, DeepBern-Nets, formal verification, TinyBERT.
Source attribution: curated from arXiv cs.LG (@Ibrahim Albool, Yasser Shoukry).