AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training With Crafted Input Noise

Souvik Kundu, Massoud Pedram, Peter A. Beerel

ICCV 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Defenses against universal perturbations · 86 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add crafted-noise training across time-step periods (HIRE-SNN) to traditional SNN trainingdirect-input SNN · CIFAR-10 white-boxaccuracy under attack: up to 12.2% improvement over traditional SNN trainingImproved
add crafted-noise training (HIRE-SNN) to traditional SNN trainingdirect-input SNN · CIFAR-100 white-boxaccuracy under attack: up to 8.8%Improved
add crafted-noise training (HIRE-SNN) to traditional SNN trainingdirect-input SNN · CIFAR-10 black-boxaccuracy under attack: up to 13.7%Improved
add crafted-noise training (HIRE-SNN) to traditional SNN trainingdirect-input SNN · CIFAR-100 black-boxaccuracy under attack: up to 10.4%Improved
use crafted gradient-based noise instead of Gaussian noise in training (ablation)HIRE-SNN VGG11 · CIFAR-100 white-boxaccuracy under attack: up to 6.5%Improved
use crafted gradient-based noise instead of Gaussian noise in training (ablation)HIRE-SNN VGG11 · CIFAR-100 black-boxaccuracy under attack: up to 9.7%Improved
add Gaussian noise training in place of traditional training (ablation)SNN VGG11 · CIFAR-100 white-box and black-boxaccuracy under attackNo clear effect
add crafted-noise training when threshold and leak are frozen (ablation)HIRE-SNN VGG5 · CIFAR-10 white-box PGDaccuracy under attack: 4.5 -> 13.6Improved
add crafted-noise training when threshold and leak are frozen (ablation)HIRE-SNN VGG5 · CIFAR-10 black-box PGDaccuracy under attack: 8.8 -> 21.9Improved
make threshold and leak trainable (ablation)HIRE-SNN VGG5 · CIFAR-10 cleanaccuracy: 86.8 -> 87.5Improved
increase noise step eps_s from 0.01 to 0.03 (ablation)HIRE-SNN VGG5 and VGG11 · CIFAR-10 and CIFAR-100adversarial vs clean accuracy: drop in clean image performance of up to ~2%Mixed
add period-wise weight update with noise crafting (N=2) to traditional trainingHIRE-SNN · VGG5/VGG11/ResNet12 training costGPU memory: up to ~25% less memory, no extra training timeImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy