AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN

Huy Phan, Cong Shi, Yi Xie, Tianfang Zhang, Zhuohang Li, Tianming Zhao, Jian Liu, Yan Wang, Yingying Chen, Bo Yuan

ECCV 2022 · Adversarial robustness and security › Backdoor and poisoning · approach: Trigger-based backdoor attacks · 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
learn pruning and backdoor jointly in parallel (P+B) instead of backdoor injection then pruning (B->P) (ablation)RIBAC · CIFAR-10 (16x, all-to-all)attack success rate (%): 69.50 -> 100.00Improved
learn pruning and backdoor jointly in parallel (P+B) instead of B->P (ablation)RIBAC · Tiny ImageNet (32x, all-to-all)attack success rate (%): 0.50 -> 99.28Improved
use parallel P+B instead of pruning a clean pre-trained network then WaNet backdoor training (ablation)RIBAC · Tiny ImageNet (32x, all-to-all)attack success rate (%): 53.06 -> 99.28Improved
use parallel P+B instead of random-init sparse model with WaNet training (ablation)RIBAC · CIFAR-10 (32x, all-to-all)clean accuracy (%): 89.25 -> 92.39Improved
use parallel P+B instead of B->P (ablation)RIBAC · CelebA (16x, all-to-all)clean accuracy (%): 27.16 -> 81.68Improved
use RIBAC (backdoor plus pruning) instead of L1 pruning aloneL1 pruning · CIFAR-10 (32x)clean accuracy (%): 91.51 -> 91.77No clear effect
use RIBAC instead of L1 pruning aloneL1 pruning · Tiny ImageNet (32x)clean accuracy (%): 55.64 -> 53.98No clear effect
use RIBAC instead of importance-score pruning aloneimportance-score pruning · CIFAR-10 (32x)clean accuracy (%): 93.05 -> 91.77Hurt
use RIBAC instead of existing backdoor methods without compressionWaNet/LIRA/WB · Tiny ImageNetclean accuracy and attack success rate: up to 2.76% clean accuracy and 40.64% attack success rate increaseImproved
use RIBAC instead of WaNet in all-to-all modeWaNet · Tiny ImageNet (all-to-all)attack success rate (%): 58.00 -> 99.31Improved
increase compression ratio from 2x to 32xRIBAC (all-to-one) · CIFAR-10clean accuracy (%): 94.35 -> 91.77Hurt
increase compression ratio from 2x to 32xRIBAC (all-to-all) · GTSRBattack success rate (%): 99.98 -> 98.34Hurt

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