EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry

Backdoor attack injects malicious behavior to models such that inputs embedded with triggers are misclassified to a target label desired by the attacker. However, natural features may behave like triggers, causing misclassification once embedded. While they are inevitable, mis-recognizing them as injected triggers causes false warnings in backdoor scanning. A prominent challenge is hence to distinguish natural features and injected backdoors. We develop a novel symmetric feature differencing method that identifies a smallest set of features separating two classes. A backdoor is considered injected if the corresponding trigger consists of features different from the set of features distinguishing the victim and target classes. We evaluate the technique on thousands of models, including both clean and trojaned models, from the TrojAI rounds 2-4 competitions and a number of models on ImageNet. Existing backdoor scanning techniques may produce hundreds of false positives (i.e., clean models recognized as trojaned). Our technique removes 78-100% of the false positives (by a state-of-the-art scanner ABS) with a small increase of false negatives by 0-30%, achieving 17-41% overall accuracy improvement, and facilitates achieving top performance on the leaderboard. It also boosts performance of other scanners. It outperforms false positive removal methods using L2 distance and attribution techniques. We also demonstrate its potential in detecting a number of semantic backdoor attacks.