# Dynamic Slicing for Deep Neural Networks

arXiv: https://arxiv.org/abs/2009.13747 · HTML: https://mlsanity.com/paper/2009.13747/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 16 of 16)

- [DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection](https://mlsanity.com/paper/2101.06896/) (2021)
- [ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection](https://mlsanity.com/paper/2106.08890/) (2021)
- [SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget](https://mlsanity.com/paper/2308.15030/) (2023)
- [TransTailor: Pruning the Pre-trained Model for Improved Transfer Learning](https://mlsanity.com/paper/2103.01542/) (2021)
- [FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons](https://mlsanity.com/paper/2204.02567/) (2022)
- [No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML](https://mlsanity.com/paper/2310.07152/) (2023)
- [PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing](https://mlsanity.com/paper/2111.10481/) (2021)
- [Modularizing while Training: A New Paradigm for Modularizing DNN Models](https://mlsanity.com/paper/2306.09376/) (2023)
- [TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models](https://mlsanity.com/paper/2411.09945/) (2024)
- [Supervised Robustness-preserving Data-free Neural Network Pruning](https://mlsanity.com/paper/2204.00783/) (2022)
- [NeuSemSlice: Towards Effective DNN Model Maintenance via Neuron-level Semantic Slicing](https://mlsanity.com/paper/2407.20281/) (2024)
- [IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models](https://mlsanity.com/paper/2502.07072/) (2025)
- [SliceGX: Layer-wise GNN Explanation with Model-slicing](https://mlsanity.com/paper/2506.17977/) (2025)
- [DSperse: A Framework for Targeted Verification in Zero-Knowledge Machine Learning](https://mlsanity.com/paper/2508.06972/) (2025)
- [Generative Model for Models: Rapid DNN Customization for Diverse Tasks and Resource Constraints](https://mlsanity.com/paper/2308.15003/) (2023)
- [Anomaly Detection Based on Critical Paths for Deep Neural Networks](https://mlsanity.com/paper/2505.14967/) (2025)

## Abstract (arXiv)

Program slicing has been widely applied in a variety of software engineering tasks. However, existing program slicing techniques only deal with traditional programs that are constructed with instructions and variables, rather than neural networks that are composed of neurons and synapses. In this paper, we propose NNSlicer, the first approach for slicing deep neural networks based on data flow analysis. Our method understands the reaction of each neuron to an input based on the difference between its behavior activated by the input and the average behavior over the whole dataset. Then we quantify the neuron contributions to the slicing criterion by recursively backtracking from the output neurons, and calculate the slice as the neurons and the synapses with larger contributions. We demonstrate the usefulness and effectiveness of NNSlicer with three applications, including adversarial input detection, model pruning, and selective model protection. In all applications, NNSlicer significantly outperforms other baselines that do not rely on data flow analysis.