AI Paper Atlas

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

Topological Detection of Trojaned Neural Networks

Songzhu Zheng, Yikai Zhang, Hubert Wagner, Mayank Goswami, Chao Chen

NeurIPS 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Graph neural network robustness · 2 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 topological features instead of correlation-matrix featuresTrojan detector · MNIST+LeNet5ACC: 0.59±0.10 -> 0.85±0.07Improved
Use topological features instead of correlation-matrix featuresTrojan detector · MNIST+LeNet5AUC: 0.62±0.10 -> 0.89±0.04Improved
Use topological features instead of ULPTrojan detector · MNIST+ResNet18ACC: 0.71±0.14 -> 0.87±0.09Improved
Use topological features instead of ULPTrojan detector · MNIST+ResNet18AUC: 0.71±0.14 -> 0.97±0.02Improved
Use topological features instead of correlation-matrix featuresTrojan detector · CIFAR10+ResNet18ACC: 0.72±0.07 -> 0.93±0.06Improved
Use topological features instead of correlation-matrix featuresTrojan detector · CIFAR10+ResNet18AUC: 0.81±0.08 -> 0.97±0.02Improved
Use topological features instead of DFTNDTrojan detector · CIFAR10+Densenet121ACC: 0.59±0.07 -> 0.84±0.04Improved
Use topological features instead of correlation-matrix featuresTrojan detector · CIFAR10+Densenet121AUC: 0.66±0.07 -> 0.93±0.03Improved
Use topological features instead of ULPTrojan detector · Round1-ResNetACC: 0.63±0.00 -> 0.77±0.04Improved
Use topological features instead of ULPTrojan detector · Round1-ResNetAUC: 0.62±0.03 -> 0.87±0.03Improved
Use topological features instead of ULPTrojan detector · Round1-DenseNetACC: 0.63±0.06 -> 0.62±0.04Hurt
Use topological features instead of ULPTrojan detector · Round1-DenseNetAUC: 0.63±0.06 -> 0.69±0.04Improved

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