BlockDoor: Blocking Backdoor Based Watermarks in Deep Neural Networks

TL;DR

BlockDoor is a comprehensive framework designed to block all types of backdoor triggers used for watermarking neural networks, effectively reducing watermark validation accuracy while preserving model functionality.

Contribution

This work introduces BlockDoor, a novel package of techniques that detects and modifies trigger samples to prevent backdoor watermark verification in neural networks.

Findings

Reduces watermark validation accuracy by up to 98%

Maintains less than 1% drop in accuracy on clean samples

Effective across multiple datasets and neural architectures

Abstract

Adoption of machine learning models across industries have turned Neural Networks (DNNs) into a prized Intellectual Property (IP), which needs to be protected from being stolen or being used without authorization. This topic gave rise to multiple watermarking schemes, through which, one can establish the ownership of a model. Watermarking using backdooring is the most well established method available in the literature, with specific works demonstrating the difficulty in removing the watermarks, embedded as backdoors within the weights of the network. However, in our work, we have identified a critical flaw in the design of the watermark verification with backdoors, pertaining to the behaviour of the samples of the Trigger Set, which acts as the secret key. In this paper, we present BlockDoor, which is a comprehensive package of techniques that is used as a wrapper to block all three different kinds of Trigger samples, which are used in the literature as means to embed watermarks within the trained neural networks as backdoors. The framework implemented through BlockDoor is able to detect potential Trigger samples, through separate functions for adversarial noise based triggers, out-of-distribution triggers and random label based triggers. Apart from a simple Denial-of-Service for a potential Trigger sample, our approach is also able to modify the Trigger samples for correct machine learning functionality. Extensive evaluation of BlockDoor establishes that it is able to significantly reduce the watermark validation accuracy of the Trigger set by up to $98\%$ without compromising on functionality, delivering up to a less than $1\%$ drop on the clean samples. BlockDoor has been tested on multiple datasets and neural architectures.