# XploreNAS: Explore Adversarially Robust & Hardware-efficient Neural Architectures for Non-ideal Xbars

arXiv: https://arxiv.org/abs/2302.07769 · HTML: https://mlsanity.com/paper/2302.07769/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 15 Feb 2023.

## Builds on (most cited first, 19 of 19)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks](https://mlsanity.com/paper/1911.10695/) (2019)
- [Hardware/Software Co-Exploration of Neural Architectures](https://mlsanity.com/paper/1907.04650/) (2019)
- [Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks](https://mlsanity.com/paper/2002.04116/) (2020)
- [RxNN: A Framework for Evaluating Deep Neural Networks on Resistive Crossbars](https://mlsanity.com/paper/1809.00072/) (2018)
- [DANCE: Differentiable Accelerator/Network Co-Exploration](https://mlsanity.com/paper/2009.06237/) (2020)
- [TxSim:Modeling Training of Deep Neural Networks on Resistive Crossbar Systems](https://mlsanity.com/paper/2002.11151/) (2020)
- [Examining the Robustness of Spiking Neural Networks on Non-ideal Memristive Crossbars](https://mlsanity.com/paper/2206.09599/) (2022)
- [SpikeSim: An end-to-end Compute-in-Memory Hardware Evaluation Tool for Benchmarking Spiking Neural Networks](https://mlsanity.com/paper/2210.12899/) (2022)
- [Architecture Search of Dynamic Cells for Semantic Video Segmentation](https://mlsanity.com/paper/1904.02371/) (2019)
- [DetectX -- Adversarial Input Detection using Current Signatures in Memristive XBar Arrays](https://mlsanity.com/paper/2106.12021/) (2021)
- [Examining and Mitigating the Impact of Crossbar Non-idealities for Accurate Implementation of Sparse Deep Neural Networks](https://mlsanity.com/paper/2201.05229/) (2022)
- [Efficiency-driven Hardware Optimization for Adversarially Robust Neural Networks](https://mlsanity.com/paper/2105.04003/) (2021)
- [On the Intrinsic Robustness of NVM Crossbars Against Adversarial Attacks](https://mlsanity.com/paper/2008.12016/) (2020)

## Built on by (most cited first, 1 of 1)

- [LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks](https://mlsanity.com/paper/2606.10294/) (2026)

## Abstract (arXiv)

Compute In-Memory platforms such as memristive crossbars are gaining focus as they facilitate acceleration of Deep Neural Networks (DNNs) with high area and compute-efficiencies. However, the intrinsic non-idealities associated with the analog nature of computing in crossbars limits the performance of the deployed DNNs. Furthermore, DNNs are shown to be vulnerable to adversarial attacks leading to severe security threats in their large-scale deployment. Thus, finding adversarially robust DNN architectures for non-ideal crossbars is critical to the safe and secure deployment of DNNs on the edge. This work proposes a two-phase algorithm-hardware co-optimization approach called XploreNAS that searches for hardware-efficient & adversarially robust neural architectures for non-ideal crossbar platforms. We use the one-shot Neural Architecture Search (NAS) approach to train a large Supernet with crossbar-awareness and sample adversarially robust Subnets therefrom, maintaining competitive hardware-efficiency. Our experiments on crossbars with benchmark datasets (SVHN, CIFAR10 & CIFAR100) show upto ~8-16% improvement in the adversarial robustness of the searched Subnets against a baseline ResNet-18 model subjected to crossbar-aware adversarial training. We benchmark our robust Subnets for Energy-Delay-Area-Products (EDAPs) using the Neurosim tool and find that with additional hardware-efficiency driven optimizations, the Subnets attain ~1.5-1.6x lower EDAPs than ResNet-18 baseline.