AI Paper Atlas

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

All You Need Is RAW: Defending against Adversarial Attacks with Camera Image Pipelines

Yuxuan Zhang, Bo Dong, Felix Heide

ECCV 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Adversarial perturbations beyond images

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
train F and G on real RAW (Zurich) instead of synthesized RAW (MIT) (ablation)RAW-domain defense · ImageNet FGSMTop-1 accuracy (%): 40.52 -> 58.85Improved
train on real RAW (Zurich) instead of synthesized RAW (MIT) (ablation)RAW-domain defense · ImageNet C&WTop-1 accuracy (%): 55.13 -> 71.40Improved
train on HDR-RAW-RGB instead of Zurich real RAW (ablation)RAW-domain defense · ImageNet FGSM, C&WTop-1 accuracy (%): 58.85 -> 55.57 (FGSM), 71.40 -> 71.65 (C&W)Mixed
map through RAW instead of gamma-adjusted stage (ablation)RAW-domain defense · ImageNet FGSMTop-1 accuracy (%): 44.4 -> 57.33Improved
map through RAW instead of demosaic stage (ablation)RAW-domain defense · ImageNet FGSMTop-1 accuracy (%): 52.93 -> 57.33Improved
map through RAW instead of gamma stage (ablation)RAW-domain defense · ImageNet PGDTop-1 accuracy (%): 71% -> 53%Improved
add G operator to the S operator (omega 0 to 0.7) (ablation)RAW-domain defense · ImageNet FGSMTop-1 accuracy (%): 64.25 -> 66.02Improved
add S operator to the G operator (omega 1 to 0.7) (ablation)RAW-domain defense · ImageNet FGSMTop-1 accuracy (%): 65.39 -> 66.02Improved
add Gaussian noise sigma 0.5 to F output (ablation)RAW-domain defense · ImageNet FGSMTop-1 accuracy (%): 66.02 -> 65.64No clear effect
mix F and G operators from different checkpoints (ablation)RAW-domain defense · ImageNetTop-1 accuracy (%): 66.02 -> 65.89No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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