DetectX—Adversarial Input Detection Using Current Signatures in Memristive XBar Arrays

Moitra, Abhishek; Panda, Priyadarshini

doi:10.1109/tcsi.2021.3110487

Cited by 7 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Computational overhead: Besides high adversarial detection, our method requires ∼ 10×−100× less number of operations and parameters for adversarial detection compared to works [11,22,25,29,30]. Although we require more parameters compared to [23], the number of computations in our detection is significantly less. This makes our approach suitable for deployment in resource constrained computing systems.…”

Section: Comparison With Prior Workmentioning

confidence: 98%

“…Here, the target models are trained on natural inputs with different feature squeezing techniques at the inputs. Moitra et al [23] uses the features from the first layer of the underlying model to perform adversarial detection. In particular, they perform adversarial detection using hardware signatures in DNN accelerators.…”

Section: Work Requiring Target Model Trainingmentioning

confidence: 99%

Section: Sequential Layer-wise Training and Analysismentioning

confidence: 99%

“…Note, our training objective is loosely based on the current signature separation in recent work [23]. We would like to highlight that [23] focuses on modifying the target model's layers to perform adversary detection. In contrast, we train the detector independently that enables high detection scores along with transferability across multiple datasets and attacks.…”

Section: Sequential Layer-wise Training and Analysismentioning

confidence: 99%

“…Metzen et al [22], Yin et al [30], and Sterneck et al [25] train neural network-based detectors on the intermediate features of the target model for adversarial detection. On the other hand, Xu et al [29] and Moitra et al [23] train the target model for improving the adversarial detectability. Gong et al [11] propose a binary classifier approach that requires adversarial data generated using the target model for training.…”

Section: Comparison With Prior Workmentioning

confidence: 99%

See 4 more Smart Citations

Adversarial Detection without Model Information

Moitra¹,

Kim²,

Panda³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Most prior state-of-the-art adversarial detection works assume that the underlying vulnerable model is accessible,i.e., the model can be trained or its outputs are visible. However, this is not a practical assumption due to factors like model encryption, model information leakage and so on. In this work, we propose a model independent adversarial detection method using a simple energy function to distinguish between adversarial and natural inputs. We train a standalone detector independent of the underlying model, with sequential layer-wise training to increase the energy separation corresponding to natural and adversarial inputs. With this, we perform energy distribution-based adversarial detection. Our method achieves state-of-the-art detection performance (ROC-AUC > 0.9) across a wide range of gradient, score and decision-based adversarial attacks on CIFAR10, CIFAR100 and TinyImagenet datasets. Compared to prior approaches, our method requires ∼ 10-100x less number of operations and parameters for adversarial detection. Further, we show that our detection method is transferable across different datasets and adversarial attacks. For reproducibility, we provide code in the supplementary material.

show abstract

Section: Comparison With Prior Workmentioning

confidence: 98%

Section: Work Requiring Target Model Trainingmentioning

confidence: 99%

Section: Sequential Layer-wise Training and Analysismentioning

confidence: 99%

Section: Sequential Layer-wise Training and Analysismentioning

confidence: 99%

Section: Comparison With Prior Workmentioning

confidence: 99%

See 3 more Smart Citations

Adversarial Detection without Model Information

Moitra¹,

Kim²,

Panda³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Robustness for Embedded Machine Learning Using In-Memory Computing

Panda,

Bhattacharjee,

Moitra

2023

Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing

View full text Add to dashboard Cite

When in-memory computing meets spiking neural networks—A perspective on device-circuit-system-and-algorithm co-design

Moitra,

Bhattacharjee,

et al. 2024

Applied Physics Reviews

View full text Add to dashboard Cite

This review explores the intersection of bio-plausible artificial intelligence in the form of spiking neural networks (SNNs) with the analog in-memory computing (IMC) domain, highlighting their collective potential for low-power edge computing environments. Through detailed investigation at the device, circuit, and system levels, we highlight the pivotal synergies between SNNs and IMC architectures. Additionally, we emphasize the critical need for comprehensive system-level analyses, considering the inter-dependencies among algorithms, devices, circuit, and system parameters, crucial for optimal performance. An in-depth analysis leads to the identification of key system-level bottlenecks arising from device limitations, which can be addressed using SNN-specific algorithm–hardware co-design techniques. This review underscores the imperative for holistic device to system design-space co-exploration, highlighting the critical aspects of hardware and algorithm research endeavors for low-power neuromorphic solutions.

show abstract

DetectX—Adversarial Input Detection Using Current Signatures in Memristive XBar Arrays

Cited by 7 publications

References 21 publications

Adversarial Detection without Model Information

Adversarial Detection without Model Information

Robustness for Embedded Machine Learning Using In-Memory Computing

When in-memory computing meets spiking neural networks—A perspective on device-circuit-system-and-algorithm co-design

Contact Info

Product

Resources

About