AI Paper Atlas

Research map / Adversarial robustness and security / Backdoor and poisoning

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch

Hossein Souri, Liam H Fowl, Rama Chellappa, Micah Goldblum, Tom Goldstein

NeurIPS 2022 · Adversarial robustness and security › Backdoor and poisoning · approach: Trigger-based backdoor attacks · 10 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 Sleeper Agent hidden-trigger poisoningResNet-18 trained from scratch · CIFAR-10Attack Success Rate (%): 3.50 \% -> 78.84\%Improved
Use Sleeper Agent hidden-trigger poisoningMobileNetV2 trained from scratch · CIFAR-10Attack Success Rate (%): 3.76 \% -> 75.96\%Improved
Use Sleeper Agent hidden-trigger poisoningVGG11 trained from scratch · CIFAR-10Attack Success Rate (%): 5.02 \% -> 86.60\%Improved
Increase poison budget from 0.1% to 1%Sleeper Agent on ResNet-18 · CIFAR-10Attack Success Rate (%): 24.71\ (\pm 4.10) -> 85.27\ (\pm 5.90)Improved
Randomize patch location rather than fixing it (ablation)Sleeper Agent on ResNet-18 · CIFAR-10Attack Success Rate (%): 19.25\ (\pm 3.01) -> 33.95 \ (\pm 4.57)Improved
Add surrogate retraining during poison crafting (ablation)Sleeper Agent with random patch location · CIFAR-10Attack Success Rate (%): 33.95 \ (\pm 4.57) -> 59.42 \ (\pm 5.78)Improved
Select poisons by maximum gradient norm (ablation)Sleeper Agent with random patch location · CIFAR-10Attack Success Rate (%): 33.95 \ (\pm 4.57) -> 63.49 \ (\pm 6.13)Improved
Combine retraining and gradient-norm data selection (ablation)Sleeper Agent with random patch location · CIFAR-10Attack Success Rate (%): 33.95 \ (\pm 4.57) -> 85.27 \ (\pm 5.90)Improved
Retrain the surrogate twice during crafting (ablation)Sleeper Agent · ImageNetAttack Success Rate (%): 22.00 \ (\pm 5.65) -> 44.00 \ (\pm 6.73)Improved
Increase retraining factor from T=4 to T=8 (ablation)Sleeper Agent on ResNet-18 · CIFAR-10Attack Success Rate (%): 85.27 \ (\pm 5.90) -> 86.48 \ (\pm 6.26)No clear effect
Increase the perturbation bound from 8/255 to 16/255Sleeper Agent on ResNet-18 · CIFAR-10Attack Success Rate (%): 37.32 \ (\pm 8.33) -> 85.27 \ (\pm 5.90)Improved
Increase same-architecture ensemble size from S=1 to S=4Sleeper Agent without retraining · CIFAR-10Attack Success Rate (%): 63.49\ (\pm 6.13) -> 74.81 \ (\pm 4.10)Improved

Later papers that compared with this method

4 later accepted papers report Sleeper Agent as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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