当前位置: X-MOL 学术arXiv.cs.LO › 论文详情
ReluDiff: Differential Verification of Deep Neural Networks
arXiv - CS - Logic in Computer Science Pub Date : 2020-01-10 , DOI: arxiv-2001.03662
Brandon Paulsen; Jingbo Wang; Chao Wang

As deep neural networks are increasingly being deployed in practice, their efficiency has become an important issue. While there are compression techniques for reducing the network's size, energy consumption and computational requirement, they only demonstrate empirically that there is no loss of accuracy, but lack formal guarantees of the compressed network, e.g., in the presence of adversarial examples. Existing verification techniques such as Reluplex, ReluVal, and DeepPoly provide formal guarantees, but they are designed for analyzing a single network instead of the relationship between two networks. To fill the gap, we develop a new method for differential verification of two closely related networks. Our method consists of a fast but approximate forward interval analysis pass followed by a backward pass that iteratively refines the approximation until the desired property is verified. We have two main innovations. During the forward pass, we exploit structural and behavioral similarities of the two networks to more accurately bound the difference between the output neurons of the two networks. Then in the backward pass, we leverage the gradient differences to more accurately compute the most beneficial refinement. Our experiments show that, compared to state-of-the-art verification tools, our method can achieve orders-of-magnitude speedup and prove many more properties than existing tools.
更新日期:2020-01-14

 

全部期刊列表>>
施普林格自然
最近合集,配们化学
欢迎访问IOP中国网站
GIANT
自然职场线上招聘会
ACS ES&T Engineering
ACS ES&T Water
屿渡论文,编辑服务
何川
苏昭铭
陈刚
姜涛
李闯创
复旦大学
刘立明
隐藏1h前已浏览文章
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
天合科研
x-mol收录
上海纽约大学
曾林
天津大学
何振宇
史大永
吉林大学
卓春祥
张昊
刘冬生
试剂库存
down
wechat
bug