Solving the Capsulation Attack against Backdoor-based Deep Neural Network Watermarks by Reversing Triggers

Fangqi Li, Shilin Wang, Yun ZhuarXiv 2022 · DOI · arXiv

Abstract

Deep Neural Network (DNN) watermarking using backdoor triggers is a common method for intellectual property protection. However, these watermarks are often vulnerable to "Capsulation Attacks," where an adversary uses a filter to detect and block verification triggers. This paper introduces CAScore, a metric to quantify trigger detectability, and proposes a novel reverse-backdoor scheme. By utilizing normal data samples as triggers and chaining them via cryptographic hashes, the proposed method achieves near-perfect indistinguishability (CAScore of 0.99) and robust resistance against filtering attacks without compromising model performance.

Introduction

Training state-of-the-art Deep Neural Networks (DNNs) requires significant computational resources and high-quality datasets, making them valuable intellectual property. To protect these assets, model owners often embed "watermarks" using backdoor techniques. In a black-box verification setting, an owner proves ownership by demonstrating that the model produces specific, pre-defined outputs when presented with "trigger" inputs—typically images containing specific stamps or noise patterns.

However, a significant vulnerability exists: most current triggers are statistical outliers. If a pirate steals a model and suspects it is watermarked, they can implement a "Capsulation Attack."

The Capsulation Attack and CAScore

In a Capsulation Attack, the pirate places a filter (a "capsule") in front of the stolen model. This filter is designed to distinguish between normal user queries and potential verification triggers. When a trigger is detected, the filter returns a fake or neutral result, effectively "muting" the owner's evidence and preventing successful verification.

The Capsulation Attack model, where a filter $f$ intercepts potential triggers.

To quantify this vulnerability, the authors propose CAScore (Capsulation Attack Score). This metric is based on the Area Under the Curve (AUC) of a binary classifier trained to distinguish triggers from normal data. A CAScore of 1.0 indicates that triggers are perfectly indistinguishable from the natural data distribution, while a score near 0.0 indicates they are trivial to filter.

The Reverse-Backdoor Scheme

To counter the Capsulation Attack, the authors propose a "reverse-backdoor" scheme. Instead of using artificial, "weird" triggers, this method selects normal samples from the training set to serve as triggers.

Methodology

The scheme relies on three key components:

  1. Encoding: A pseudorandom inverse generator and one-way hash functions are used to chain normal samples together.
  2. Verification: During ownership proof, the owner submits these normal-looking triggers in a randomized sequence. Because the triggers belong to the natural data distribution, a pirate's filter cannot block them without also degrading the model's performance on legitimate user queries.
  3. Merkle Trees: To ensure the integrity of the trigger set, Merkle hashes provide a compact and unforgeable proof of identity.
The verification process of the Reverse-Backdoor scheme, utilizing inverse transformations and hash chaining.

Experimental Evaluation

The authors evaluated the proposed scheme using standard benchmarks, including MNIST and CIFAR-10, with ResNet architectures.

Key Results

  • Indistinguishability: Traditional watermarking methods (e.g., noise, steganography) performed poorly on the CAScore test, with scores between 0.00 and 0.08. In contrast, the Reverse-Backdoor scheme achieved a near-perfect 0.99.
  • Robustness: Under a Capsulation Attack using a Bayes filter, traditional schemes failed to verify ownership. The Reverse-Backdoor triggers successfully bypassed the filter.
  • Performance: The watermarking process did not significantly impact the primary task accuracy of the models, maintaining performance levels comparable to unwatermarked baselines.

Conclusion and Future Work

The Reverse-Backdoor scheme effectively addresses the Capsulation Attack by hiding triggers "in plain sight" within the normal data distribution. While this provides strong protection in black-box scenarios, the authors note that "white-box" attacks (where the pirate has access to model weights) and "overwriting" attacks (where a pirate attempts to claim prior ownership) remain areas for future research. The use of distributed ledgers for timestamping is suggested as a potential mitigation for the latter.

Summary updated

Abstract

Backdoor-based watermarking schemes were proposed to protect the intellectual property of artificial intelligence models, especially deep neural networks, under the black-box setting. Compared with ordinary backdoors, backdoor-based watermarks need to digitally incorporate the owner's identity, which fact adds extra requirements to the trigger generation and verification programs. Moreover, these concerns produce additional security risks after the watermarking scheme has been published for as a forensics tool or the owner's evidence has been eavesdropped on. This paper proposes the capsulation attack, an efficient method that can invalidate most established backdoor-based watermarking schemes without sacrificing the pirated model's functionality. By encapsulating the deep neural network with a rule-based or Bayes filter, an adversary can block ownership probing and reject the ownership verification. We propose a metric, CAScore, to measure a backdoor-based watermarking scheme's security against the capsulation attack. This paper also proposes a new backdoor-based deep neural network watermarking scheme that is secure against the capsulation attack by reversing the encoding process and randomizing the exposure of triggers.
BibTeX
@misc{li2022solving,
  author = {Fangqi Li and Shilin Wang and Yun Zhu},
  title = {{Solving the Capsulation Attack against Backdoor-based Deep Neural Network Watermarks by Reversing Triggers}},
  year = {2022},
  eprint = {2208.14127},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2208.14127},
}
Figure