AI Paper Atlas

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

Towards Effective and Robust Neural Trojan Defenses via Input Filtering

Kien Do, Haripriya Harikumar, Hung Le, Dung Nguyen, Truyen Tran, Santu Rana, Dang Nguyen, Willy Susilo, Svetha Venkatesh

ECCV 2022 · Adversarial robustness and security › Certified and empirical robustness · approach: Attack evaluation and defense critique · 8 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 KL (lossy compression) term, IF -> VIF (ablation)IF · CIFAR10 (image-BI+)Trojan accuracy T (%): 37.48 -> 10.52Improved
add adversarial trigger generator, IF -> AIF (ablation)IF · CIFAR10 (image-BI+)Trojan accuracy T (%): 37.48 -> 1.96Improved
add KL term, IF -> VIF (ablation)IF · GTSRB (image-BI+)Trojan accuracy T (%): 52.27 -> 12.12Improved
add adversarial training, IF -> AIF (ablation)IF · CelebA (image-BI+)Trojan accuracy T (%): 59.39 -> 18.40Improved
add KL term, IF -> VIF (ablation)IF · CIFAR10 (benign model)decrease in clean accuracy (%): 3.34 -> 7.81Hurt
add adversarial training, IF -> AIFVIF · CIFAR10 (benign model)decrease in clean accuracy (%): 7.81 -> 4.67Improved
add filtering-then-contrasting to AIFAIF · CIFAR10 (image-BI+)FPR/FNR vs T: 1.96 -> 2.15No clear effect
add FtC to filtering defense for large-norm BadNet+ triggers (s=23) (ablation)IF/VIF · CIFAR10 (BadNet+ s=23)Trojan detection FNR (%): 64.41 -> 63.74Improved
use Filtering-then-Contrasting instead of filtering under large-norm triggers (ablation)VIF · CIFAR10 (noise-BI+ alpha=0.7)FNR (%): 0.22 -> 0.26Improved
reduce training data with fixed epochs (proportion 1.0 -> 0.05) (ablation)IF · CIFAR10 (InpAwAtk)decrease in clean accuracy (%): 4.47 -> 25.93Hurt
reduce training data with fixed total iterations (1.0 -> 0.05) (ablation)VIF · CIFAR10 (InpAwAtk)Trojan accuracy T (%): 3.07 -> 4.67No clear effect
remove explicit trigger normalization in AIF (AIF*) (ablation)AIF · CIFAR10 (BadNet+ s=23)FNR (%): 28.0 -> 30.19Hurt

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