Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger

TL;DR

This paper introduces BAAT, a novel clean-label backdoor attack using content-relevant attribute triggers, which is more stealthy and effective against defenses compared to existing sample-specific backdoor attacks.

Contribution

Proposes BAAT, a new attack paradigm that uses human-relied attributes as triggers, enhancing stealthiness and attack success in clean-label backdoor attacks.

Findings

BAAT effectively bypasses existing defenses.

Attribute triggers improve attack stealthiness.

Experimental results confirm BAAT's high success rate.

Abstract

Currently, sample-specific backdoor attacks (SSBAs) are the most advanced and malicious methods since they can easily circumvent most of the current backdoor defenses. In this paper, we reveal that SSBAs are not sufficiently stealthy due to their poisoned-label nature, where users can discover anomalies if they check the image-label relationship. In particular, we demonstrate that it is ineffective to directly generalize existing SSBAs to their clean-label variants by poisoning samples solely from the target class. We reveal that it is primarily due to two reasons, including \textbf{(1)} the `antagonistic effects' of ground-truth features and \textbf{(2)} the learning difficulty of sample-specific features. Accordingly, trigger-related features of existing SSBAs cannot be effectively learned under the clean-label setting due to their mild trigger intensity required for ensuring stealthiness. We argue that the intensity constraint of existing SSBAs is mostly because their trigger patterns are `content-irrelevant' and therefore act as `noises' for both humans and DNNs. Motivated by this understanding, we propose to exploit content-relevant features, $a.k.a.$ (human-relied) attributes, as the trigger patterns to design clean-label SSBAs. This new attack paradigm is dubbed backdoor attack with attribute trigger (BAAT). Extensive experiments are conducted on benchmark datasets, which verify the effectiveness of our BAAT and its resistance to existing defenses.