Trojans and Adversarial Examples: A Lethal Combination

Guanxiong Liu, Issa Khalil, Abdallah Khreishah, Hai Phan

Abstract: In this work, we naturally unify adversarial examples and Trojan backdoors into a new stealthy attack, that is activated only when 1) adversarial perturbation is injected into the input examples and 2) a Trojan backdoor is used to poison the training process simultaneously. Different from traditional attacks, we leverage adversarial noise in the input space to move Trojan-infected examples across the model decision boundary, thus making it difficult to be detected. Our attack can fool the user into accidentally trusting the infected model as a robust classifier against adversarial examples. We perform a thorough analysis and conduct an extensive set of experiments on several benchmark datasets to show that our attack can bypass existing defenses with a success rate close to 100%.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=9OPL0JwUg_