mlsanityData to 7 Oct 2026

SyReNN: A Tool for Analyzing Deep Neural Networks

arXiv 2101.03263 ↗First posted 9 Jan 2021cs.LG cs.PLcited by 10

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety of important domains. Formally, DNNs are complicated vector-valued functions which come in a variety of sizes and applications. Unfortunately, modern DNNs have been shown to be vulnerable to a variety of attacks and buggy behavior. This has motivated recent work in formally analyzing the properties of such DNNs. This paper introduces SyReNN, a tool for understanding and analyzing a DNN by computing its symbolic representation. The key insight is to decompose the DNN into linear functions. Our tool is designed for analyses using low-dimensional subsets of the input space, a unique design point in the space of DNN analysis tools. We describe the tool and the underlying theory, then evaluate its use and performance on three case studies: computing Integrated Gradients, visualizing a DNN's decision boundaries, and patching a DNN.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 27 of its 76 references that are in the map. First posted on arXiv 9 Jan 2021.

Builds on

27 of 76 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  8. 2019Natural Adversarial Examplescited by 1,401
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  11. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  12. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
15 more
  1. 2016Safety Verification of Deep Neural Networkscited by 262
  2. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  3. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  4. 2018Formal Security Analysis of Neural Networks using Symbolic Intervalscited by 185
  5. 2018Verifiable Reinforcement Learning via Policy Extractioncited by 176
  6. 2019Complexity of Linear Regions in Deep Networkscited by 166
  7. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 137
  8. 2016Measuring Neural Net Robustness with Constraintscited by 90
  9. 2018Deep Neural Network Compression for Aircraft Collision Avoidance Systemscited by 58
  10. 2019Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustnesscited by 40
  11. 2019An Inductive Synthesis Framework for Verifiable Reinforcement Learningcited by 39
  12. 2019FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Networkcited by 38
  13. 2017Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activationscited by 22
  14. 2018Reachable Set Estimation and Safety Verification for Piecewise Linear Systems with Neural Network Controllerscited by 15
  15. 2019Computing Linear Restrictions of Neural Networkscited by 14

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 1; 2023: 4; 2024: 1.

10 papers.

  1. 2021Provable Repair of Deep Neural Networkscited by 39
  2. 2021Neural Network Repair with Reachability Analysiscited by 19
  3. 2023Provable Preimage Under-Approximation for Neural Networks (Full Version)cited by 13
  4. 2023Architecture-Preserving Provable Repair of Deep Neural Networkscited by 9
  5. 2024PREMAP: A Unifying PREiMage APproximation Framework for Neural Networkscited by 8
  6. 2023When to Trust AI: Advances and Challenges for Certification of Neural Networkscited by 6
  7. 2021Assessment of Neural Networks for Stream-Water-Temperature Predictioncited by 1
  8. 2022Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbationscited by 1
  9. 2021Permutation Invariance of Deep Neural Networks with ReLUscited by 0
  10. 2023The inverse problem for neural networkscited by 0