Cassandra: Detecting Trojaned Networks from Adversarial Perturbations

28 Jul 2020Xiaoyu ZhangAjmal MianRohit GuptaNazanin RahnavardMubarak Shah

Deep neural networks are being widely deployed for many critical tasks due to their high classification accuracy. In many cases, pre-trained models are sourced from vendors who may have disrupted the training pipeline to insert Trojan behaviors into the models... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Adversarial Defense TrojAI Round 0 Cassandra Detection Accuracy 92.5±1.1 # 1
Adversarial Defense TrojAI Round 1 Cassandra Detection Accuracy 92.0 ± 1.3 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet