Deep learning-based techniques have achieved stateof-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation on many GPUs; as a result, many users outsource the training procedure to the cloud or rely on pre-trained models that are then fine-tuned for a specific task. In this paper we show that outsourced training introduces new security risks: an adversary can create a maliciously trained network (a backdoored neural network, or a BadNet) that has state-of-theart performance on the user's training and validation samples, but behaves badly on specific attacker-chosen inputs. We first explore the properties of BadNets in a toy example, by creating a backdoored handwritten digit classifier. Next, we demonstrate backdoors in a more realistic scenario by creating a U.S. street sign classifier that identifies stop signs as speed limits when a special sticker is added to the stop sign; we then show in addition that the backdoor in our US street sign detector can persist even if the network is later retrained for another task and cause a drop in accuracy of 25% on average when the backdoor trigger is present. These results demonstrate that backdoors in neural networks are both powerful and-because the behavior of neural networks is difficult to explicatestealthy. This work provides motivation for further research into techniques for verifying and inspecting neural networks, just as we have developed tools for verifying and debugging software.

Deep learning-based techniques have achieved state-of-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation on many GPUs; as a result, many users outsource the training procedure to the cloud or rely on pre-trained models that are then fine-tuned for a specific task. In this paper, we show that the outsourced training introduces new security risks: an adversary can create a maliciously trained network (a backdoored neural network, or a BadNet) that has the state-of-the-art performance on the user's training and validation samples but behaves badly on specific attacker-chosen inputs. We first explore the properties of BadNets in a toy example, by creating a backdoored handwritten digit classifier. Next, we demonstrate backdoors in a more realistic scenario by creating a U.S. street sign classifier that identifies stop signs as speed limits when a special sticker is added to the stop sign; we then show in addition that the backdoor in our U.S. street sign detector can persist even if the network is later retrained for another task and cause a drop in an accuracy of 25% on average when the backdoor trigger is present. These results demonstrate that backdoors in neural networks are both powerful and-because the behavior of neural networks is difficult to explicate-stealthy. This paper provides motivation for further research into techniques for verifying and inspecting neural networks, just as we have developed tools for verifying and debugging software. INDEX TERMS Computer security, machine learning, neural networks.

Deep neural networks (DNNs) provide excellent performance across a wide range of classification tasks, but their training requires high computational resources and is often outsourced to third parties. Recent work has shown that outsourced training introduces the risk that a malicious trainer will return a backdoored DNN that behaves normally on most inputs but causes targeted misclassifications or degrades the accuracy of the network when a trigger known only to the attacker is present. In this paper, we provide the first effective defenses against backdoor attacks on DNNs. We implement three backdoor attacks from prior work and use them to investigate two promising defenses, pruning and fine-tuning. We show that neither, by itself, is sufficient to defend against sophisticated attackers. We then evaluate fine-pruning, a combination of pruning and fine-tuning, and show that it successfully weakens or even eliminates the backdoors, i.e., in some cases reducing the attack success rate to 0% with only a 0.4% drop in accuracy for clean (non-triggering) inputs. Our work provides the first step toward defenses against backdoor attacks in deep neural networks.

No abstract

No abstract