Poison Ink: Robust and Invisible Backdoor Attack

TL;DR

Poison Ink introduces a robust, invisible backdoor attack method that leverages image structures and deep embedding to achieve high stealthiness and resistance against defenses across various datasets and models.

Contribution

The paper proposes Poison Ink, a novel backdoor attack that is both robust to data transformations and invisible, outperforming existing methods in stealthiness and resilience.

Findings

Outperforms existing backdoor methods in stealthiness and robustness.

Effective across multiple datasets and neural network architectures.

Resistant to many state-of-the-art defense techniques.

Abstract

Recent research shows deep neural networks are vulnerable to different types of attacks, such as adversarial attack, data poisoning attack and backdoor attack. Among them, backdoor attack is the most cunning one and can occur in almost every stage of deep learning pipeline. Therefore, backdoor attack has attracted lots of interests from both academia and industry. However, most existing backdoor attack methods are either visible or fragile to some effortless pre-processing such as common data transformations. To address these limitations, we propose a robust and invisible backdoor attack called "Poison Ink". Concretely, we first leverage the image structures as target poisoning areas, and fill them with poison ink (information) to generate the trigger pattern. As the image structure can keep its semantic meaning during the data transformation, such trigger pattern is inherently robust to data transformations. Then we leverage a deep injection network to embed such trigger pattern into the cover image to achieve stealthiness. Compared to existing popular backdoor attack methods, Poison Ink outperforms both in stealthiness and robustness. Through extensive experiments, we demonstrate Poison Ink is not only general to different datasets and network architectures, but also flexible for different attack scenarios. Besides, it also has very strong resistance against many state-of-the-art defense techniques.