AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Accelerators

David Stutz, Nandhini Chandramoorthy, Matthias Hein, Bernt Schiele

TPAMI 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training with feature consistency · 23 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
use per-layer instead of global quantization (ablation)Normal quantization · CIFAR10 8-bit p=0.5%robust test error: 90.71 -> 24.76Improved
use asymmetric quantization into signed integers (ablation)per-layer quantization · CIFAR10 8-bit p=0.5%robust test error: 24.76 -> 40.78Hurt
quantize into unsigned integers (ablation)asymmetric quantization · CIFAR10 8-bit p=0.5%robust test error: 40.78 -> 17.00Improved
use proper rounding instead of integer conversion (ablation)RQuant · CIFAR10 8-bit p=0.5%robust test error: 17.00 -> 11.28Improved
use proper rounding at 4 bit (ablation)Clipping[0.1]+RQuant · CIFAR10 4-bit p=0.5%robust test error: 90.36 -> 7.71Improved
add weight clipping wmax=0.1RQuant · CIFAR10 8-bit p=1.5%robust test error: 68.65 -> 12.22Improved
use per-layer instead of global weight clipping (ablation)Clipping · CIFAR10 8-bit p=1.5%robust test error: 12.22 -> 8.14Improved
add label smoothing to weight clipping (ablation)Clipping[0.15] · CIFAR10 8-bit p=1%robust test error: 13.08 -> 29.40Hurt
use batch norm instead of group norm (ablation)Clipping[0.1] · CIFAR10 8-bit p=1%robust test error: 8.93 -> 18.32Hurt
tighten clipping to wmax=0.025 (ablation)Clipping · CIFAR10 8-bit p=1%robust test error: 7.18 -> 8.18Hurt
add random bit error training to global clipping (ablation)Clipping[0.1] · CIFAR10 8-bit p=1.5%robust test error: 12.22 -> 8.65Improved
add random bit error training to per-layer clipping (ablation)PLClipping[0.25] · CIFAR10 8-bit p=1.5%robust test error: 8.14 -> 7.02Improved

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