BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS

TL;DR

This paper introduces BDFirewall, a black-box defense framework against backdoor attacks in MLaaS, classifying triggers by visibility and applying tailored purification methods to effectively neutralize them without model access.

Contribution

The paper proposes a novel progressive defense framework that categorizes backdoor triggers by impact and removes them efficiently in black-box scenarios, outperforming existing methods.

Findings

Reduces attack success rate by 33.25% on average

Improves poisoned sample accuracy by 29.64%

Achieves up to 111x faster inference

Abstract

In this paper, we endeavor to address the challenges of backdoor attacks countermeasures in black-box scenarios, thereby fortifying the security of inference under MLaaS. We first categorize backdoor triggers from a new perspective, i.e., their impact on the patched area, and divide them into: high-visibility triggers (HVT), semi-visibility triggers (SVT), and low-visibility triggers (LVT). Based on this classification, we propose a progressive defense framework, BDFirewall, that removes these triggers from the most conspicuous to the most subtle, without requiring model access. First, for HVTs, which create the most significant local semantic distortions, we identify and eliminate them by detecting these salient differences. We then restore the patched area to mitigate the adverse impact of such removal process. The localized purification designed for HVTs is, however, ineffective against SVTs, which globally perturb benign features. We therefore model an SVT-poisoned input as a mixture of a trigger and benign features, where we unconventionally treat the benign features as "noise". This formulation allows us to reconstruct SVTs by applying a denoising process that removes these benign "noise" features. The SVT-free input is then obtained by subtracting the reconstructed trigger. Finally, to neutralize the nearly imperceptible but fragile LVTs, we introduce lightweight noise to disrupt the trigger pattern and then apply DDPM to restore any collateral impact on clean features. Comprehensive experiments demonstrate that our method outperforms state-of-the-art defenses. Compared with baselines, BDFirewall reduces the Attack Success Rate (ASR) by an average of 33.25%, improving poisoned sample accuracy (PA) by 29.64%, and achieving up to a 111x speedup in inference time. Code will be made publicly available upon acceptance.