AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?

Ruisi Cai, Zhenyu Zhang, Zhangyang Wang

ICML 2023 · Architectures and efficiency › RNNs and normalization · approach: Representation geometry and collapse · 0 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 shallow-5-layer RWS (16-bit) to standard modelVGG-16 standard model · CIFAR-10, CIFAR-100, Tiny-ImageNet, ResNet-50 Tiny-ImageNetaveraged robust accuracy: +19.32 / +21.86 / +20.67 (VGG-16); +23.16 (ResNet-50)Improved
patch with shallow RWS, then remove it to restore clean modelRWS patching · CIFAR-10 VGG-16clean accuracy TA: TA stays 92.59 with RWS taken offNo clear effect
restrict RWS to shallowest 5 layers instead of full model (ablation)RWS patching · CIFAR-10 VGG-16RA (%): 84.86 vs 75.35 (full RWS)Improved
16-bit quantization of shallow RWS (ablation)shallow RWS patch · CIFAR-10 VGG-16RA (%): 84.76 vs 84.86 (unquantized shallow)No clear effect
8-bit quantization of shallow RWS (ablation)shallow RWS patch · CIFAR-10 VGG-16RA (%): 82.99 vs 84.76 (16-bit)Hurt
quantize full model weights to 16 bit (ablation)standard model · CIFAR-10 VGG-16RA (%): 58.12 vs 65.44Hurt
RWS storage compression (shallow 16-bit vs full model)RWS patch · CIFAR-10 VGG-16 storageN_param (MB): 79.9 MB vs 1177.6 MB (All Models)Improved
transfer RWS from Tiny-ImageNet to ImageNet VGG-16 modelImageNet standard model · ImageNet robust accuracyrobust accuracy (%): +6.39 (17.53 vs 11.14)Improved
transfer RWS from CIFAR-10 to a model trained on another dataset (zero-shot) (ablation)CIFAR-100 and Tiny-ImageNet standard models · cross-dataset RWS transferaveraged robust accuracy: CIFAR-100 +18.89; Tiny-ImageNet +8.65Improved
data augmentation with matched FLOPS (CIFAR-10 budget) for ImageNet robustnessImageNet VGG-16 · ImageNet robust accuracyrobust accuracy (%): -0.13 (11.01 vs 11.14)Hurt

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