BIRDNN: Behavior-Imitation Based Repair for Deep Neural Networks
Neural Networks, ISSN: 0893-6080, Vol: 183, Page: 106949
2025
Metric Options: CountsSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Article Description
The increasing utilization of deep neural networks (DNNs) in safety-critical systems has raised concerns about their potential to exhibit undesirable behaviors. Consequently, DNN repair/patching arises in response to the times, and it aims to eliminate unexpected predictions generated by flawed DNNs. However, existing repair methods, both retraining- and fine-tuning-based, primarily focus on high-level abstract interpretations or inferences of state spaces, often neglecting the outputs of underlying neurons. As a result, present patching strategies become computationally prohibitive and own restricted application scope (often limited to DNNs with piecewise linear (PWL) activation functions), particularly for domain-wise repair problems (DRPs). To overcome these limitations, we introduce BIRDNN, a behavior-imitation based DNN repair framework that supports alternative retraining and fine-tuning repair paradigms for DRPs. BIRDNN employs a sampling technique to characterize DNN domain behaviors and rectifies incorrect predictions by imitating the expected behaviors of positive samples during the retraining-based repair process. As for the fine-tuning repair strategy, BIRDNN analyzes the behavior differences of neurons between positive and negative samples to pinpoint the most responsible neurons for erroneous behaviors, and then integrates particle swarm optimization algorithm (PSO) to fine-tune buggy DNNs locally. Furthermore, we have developed a prototype tool for BIRDNN and evaluated its performance on two widely used DRP benchmarks, the ACAS Xu DNN safety repair problem and the MNIST DNN robustness repair problem. The experiments demonstrate that BIRDNN features more excellent effectiveness, efficiency, and compatibility in repairing buggy DNNs comprehensively compared with state-of-the-art repair methods.
Bibliographic Details
http://www.sciencedirect.com/science/article/pii/S0893608024008785; http://dx.doi.org/10.1016/j.neunet.2024.106949; http://www.scopus.com/inward/record.url?partnerID=HzOxMe3b&scp=85211231047&origin=inward; http://www.ncbi.nlm.nih.gov/pubmed/39657529; https://linkinghub.elsevier.com/retrieve/pii/S0893608024008785; https://dx.doi.org/10.1016/j.neunet.2024.106949
Elsevier BV
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know