SwitchX: Gmin-Gmax Switching for Energy-efficient and Robust Implementation of Binarized Neural Networks on ReRAM Xbars

Journal Article · Wed May 17 00:00:00 EDT 2023 · ACM Transactions on Design Automation of Electronic Systems

DOI:https://doi.org/10.1145/3576195· OSTI ID:2422211

Bhattacharjee, Abhiroop ^[1]; Panda, Priyadarshini ^[2]

---

1. Yale Univ., New Haven, CT (United States); OSTI
2. Yale Univ., New Haven, CT (United States)

Memristive crossbars can efficiently implement Binarized Neural Networks (BNNs) wherein the weights are stored in high-resistance states (HRS) and low-resistance states (LRS) of the synapses. We propose SwitchX mapping of BNN weights onto ReRAM crossbars such that the impact of crossbar non-idealities, that lead to degradation in computational accuracy, are minimized. Essentially, SwitchX maps the binary weights in such a manner that a crossbar instance comprises of more HRS than LRS synapses. We find BNNs mapped onto crossbars with SwitchX to exhibit better robustness against adversarial attacks than the standard crossbar mapped BNNs, the baseline. Finally, we combine SwitchX with state-aware training (that further increases the feasibility of HRS states during weight mapping) to boost the robustness of a BNN on hardware. We find that this approach yields stronger defense against adversarial attacks than adversarial training, a state-of the-art software defense. We perform experiments on a VGG16 BNN with benchmark datasets (CIFAR-10, CIFAR-100 and TinyImagenet) and use Fast Gradient Sign Method (ϵ = 0.05 to 0.3) and Projected Gradient Descent (ϵ = $$\frac{2}{255}$$ to $$\frac{32}{255}$$, α = $$\frac{2}{255}$$) adversarial attacks. We show that SwitchX combined with state-aware training can yield upto ~35% improvements in clean accuracy and ~6–16% in adversarial accuracies against conventional BNNs. Furthermore, an important by-product of SwitchX mapping is increased crossbar power savings, owing to an increased proportion of HRS synapses, which is furthered with state-aware training. We obtain upto ~21–22% savings in crossbar power consumption for state-aware trained BNN mapped via SwitchX on 16 × 16 and 32 × 32 crossbars using the CIFAR-10 and CIFAR-100 datasets.

• Research Organization: Yale Univ., New Haven, CT (United States)
• Sponsoring Organization: Defense Advanced Research Projects Agency (DARPA); National Science Foundation (NSF); USDOE Office of Science (SC)
• Grant/Contract Number: SC0023198
• OSTI ID: 2422211
• Journal Information: ACM Transactions on Design Automation of Electronic Systems, Journal Name: ACM Transactions on Design Automation of Electronic Systems Journal Issue: 4 Vol. 28; ISSN 1084-4309
• Publisher: Association for Computing Machinery (ACM)
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
Binarized neural network
Computer Science
ReRAM crossbar
adversarial robustness
non-idealities
switched-mapping