2020
DOI: 10.48550/arxiv.2010.01171
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Data-Driven Certification of Neural Networks with Random Input Noise

Abstract: When using deep neural networks to operate safety-critical systems, assessing the sensitivity of the network outputs when subject to uncertain inputs is of paramount importance. Such assessment is commonly done using reachability analysis or robustness certification. However, certification techniques typically ignore localization information, while reachable set methods can fail to issue robustness guarantees. Furthermore, many advanced methods are either computationally intractable in practice or restricted t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(3 citation statements)
references
References 20 publications
0
3
0
Order By: Relevance
“…There are a number of techniques that provide robustness certifications to existing neural networks [5,6,41]. Among these methods, "randomized smoothing" seeks to achieve certified robustness at test time [19,38,49].…”
Section: A Parallel Line Of Work Focuses On Certified Robustnessmentioning
confidence: 99%
“…There are a number of techniques that provide robustness certifications to existing neural networks [5,6,41]. Among these methods, "randomized smoothing" seeks to achieve certified robustness at test time [19,38,49].…”
Section: A Parallel Line Of Work Focuses On Certified Robustnessmentioning
confidence: 99%
“…where ๐œ– and ๐œ‚ are the pre-defined error rate and the significance level, respectively, then with confidence at least 1 โˆ’ ๐œ‚, the optimal ๐œธ * ๐พ satisfies all the constraints in ฮฉ but only at most a fraction of probability measure ๐œ–, i.e., P(๐‘“ ๐Ž (๐œธ * ๐พ ) > 0) โ‰ค ๐œ–. In this work, we set P to be the uniform distribution on the ฮฉ set in (3). It is worthy mentioning that Theorem 2.5 still holds even if the uniqueness of the optimal ๐œธ * ๐พ is not required, since a unique optimal solution can always be obtained by using the Tie-break rule [9] if multiple optimal solutions exist.…”
Section: Scenario Optimizationmentioning
confidence: 99%
“…A number of formal verification techniques have been proposed for DNNs, including constraint-solving [8,16,19,22,24,32,39,47], abstract interpretation [21,37,59,60,84], layerby-layer exhaustive search [29], global optimisation [15,55,56], convex relaxation [31,49,50], functional approximation [76], reduction to two-player games [77,79], and star-set-based abstraction [66,67]. Sampling-based methods are adopted to probabilistic robustness verification in [2,3,12,45,74,75]. Most of them provide sound DNN robustness estimation in the form of a norm ball, but typically for very small networks or with pessimistic estimation of the norm ball radius.…”
Section: Related Workmentioning
confidence: 99%