The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Reluplex made more practical: Leaky ReLU
Abstract
In recent years, Deep Neural Networks (DNNs) have been experiencing rapid development and have been widely used in various fields. However, while DNNs have shown strong capabilities, their security problems have gradually been exposed. Therefore, the formal guarantee of neural network output is needed. Prior to the appearance of the Reluplex algorithm, the verification of DNNs was always a difficult problem. Reluplex algorithm is specially used to verify DNNs with ReLU activation function. This is an excellent and effective algorithm, but it cannot verify more activation functions. ReLU activation function will bring about "Dead Neuron" problem, and Leaky ReLU activation function can solve this problem, so it is necessary to verify DNNs based on Leaky ReLU activation function. Therefore, we propose the Leaky-Reluplex algorithm, which is based on the Reluplex algorithm. Leaky-Reluplex algorithm can verify DNNs based on Leaky ReLU activation function.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741
Learning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,172
(2010) · International Conference on Machine Learning · Cited by 13,995
Intriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143
de Moura, L., & Bjørner, N. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-78800-3_24 · Cited by 6,595 · cited 2×
“In this way, a DNN can be encoded as a CNF formula [21] [22], and then solved by generic SMT solvers [18]–[20].”
BackgroundMethodLinear Programming and Extensions
Dantzig, G. (1963) · RAND Corporation eBooks · doi:10.7249/r366 · Cited by 5,755
Hierarchical models of object recognition in cortex
Riesenhuber, M., & Poggio, T. (1999) · Nature Neuroscience · doi:10.1038/14819 · Cited by 3,309 · cited 1×
“In recent years, Deep Neural Networks (DNNs) [1] [2] have been experiencing rapid development and have been widely used in various fields.”
BackgroundEmpirical Evaluation of Rectified Activations in Convolutional Network
Xu, B., Wang, N., Chen, T., & Li, M. (2015) · arXiv · doi:10.48550/arxiv.1505.00853 · Cited by 2,264 · cited 1×
“Even though the reasons of their superior performances still lack rigorous justification from theoretic aspect [15], in some cases we do need to use Leaky ReLU.”
BackgroundReluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
Katz, G., Barrett, C., Dill, D. L., Julian, K., & Kochenderfer, M. J. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-63387-9_5 · Cited by 1,706
Linear Programming: Foundations and Extensions
Vanderbei, R. J. (1998) · Journal of the Operational Research Society · doi:10.1038/sj.jors.2600987 · Cited by 916
Safety Verification of Deep Neural Networks
Huang, X., Kwiatkowska, M., Wang, S., & Wu, M. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-63387-9_1 · Cited by 818
Cui, C., & Fearn, T. (2018) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2018.07.008 · Cited by 316
Linear Programming: Foundations and Extensions
Vanderbei, R. J. (1998) · Journal of the Operational Research Society · doi:10.1057/palgrave.jors.2600987 · Cited by 275
An Abstraction-Refinement Approach to Verification of Artificial Neural Networks
Pulina, L., & Tacchella, A. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-14295-6_24 · Cited by 261
Deep Neural Network Compression for Aircraft Collision Avoidance Systems
Julian, K. D., Kochenderfer, M. J., & Owen, M. P. (2019) · Journal of Guidance, Control, and Dynamics · doi:10.2514/1.g003724 · Cited by 183
Challenging SMT solvers to verify neural networks
Pulina, L., & Tacchella, A. (2012) · AI Communications · doi:10.3233/aic-2012-0525 · Cited by 169
An Incremental and Layered Procedure for the Satisfiability of Linear Arithmetic Logic
Bozzano, M., Roberto Bruttomesso, A., Cimatti, A., Junttila, T. A., van Rossum, P., Schulz, S., & Sebastiani, R. (2005) · Lecture notes in computer science · doi:10.1007/978-3-540-31980-1_21 · Cited by 72
Metadata
- Authors
- Xu, J., Li, Z., Du, B., Zhang, M., & Liu, J.
- Venue
- 2020 IEEE Symposium on Computers and Communications (ISCC)
- Publisher
- IEEE
- Published
- 2020-07
- Pages
- 1-7
- ISSN
- 1530-1346 (ISSN-L)
- OpenAlex
- W3094253649
- Cited by
- 398
- References
- 17
- FWCI
- 36.62
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.