arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.01260cs.CR
收藏

DeepiSign-G:用于自包含追踪的通用水印,在隐藏的DNN参数中盖章

DeepiSign-G: Generic Watermark to Stamp Hidden DNN Parameters for Self-contained Tracking

Alsharif Abuadbba, Nicholas Rhodes, Kristen Moore, Bushra Sabir, Shuo Wang, Yansong Gao

AI总结:

DeepiSign-G提出一种通用脆弱水印方法,在CNN和RNN参数的Walsh-Hadamard系数中嵌入元数据,实现自包含追踪,并能以近乎完美的检测率识别多种攻击而不影响模型性能。

摘要:

在自动驾驶汽车、人脸识别和情感分析等关键领域,深度学习解决方案因其错误的严重后果而需要谨慎对待。研究表明,这些模型容易受到对抗性攻击,例如数据投毒和神经木马,这些攻击可以隐蔽地操纵模型行为,从而损害可靠性和安全性。当前的防御策略(如水印)存在局限性:它们无法检测所有模型修改,并且主要关注图像领域中CNN的攻击,而忽略了RNN等其他关键架构。为了解决这些不足,我们提出了DeepiSign-G,这是一种通用的水印方法,旨在对包括CNN和RNN在内的主流DNN架构进行全面验证。DeepiSign-G通过在模型参数的Walsh-Hadamard变换系数中嵌入不可见水印来增强模型安全性。该水印具有高度敏感性和脆弱性,可确保及时检测到任何修改。与传统的哈希技术不同,DeepiSign-G允许直接在模型内部纳入大量元数据,从而实现详细的、自包含的追踪和验证。我们展示了DeepiSign-G在各种架构上的适用性,包括CNN模型(VGG、ResNets、DenseNet)和RNN(文本情感分类器)。我们在四个流行的数据集上进行了实验:VGG Face、CIFAR10、GTSRB Traffic Sign和Large Movie Review。我们还在五种潜在攻击下评估了DeepiSign-G。我们的综合评估证实,DeepiSign-G能够有效检测这些攻击,同时不损害CNN和RNN模型的性能,凸显了其作为深度学习应用鲁棒安全措施的有效性。完整性破坏的检测几乎完美,而仅在约1%的Walsh-Hadamard系数中隐藏一个比特。

英文摘要:

Deep learning solutions in critical domains like autonomous vehicles, facial recognition, and sentiment analysis require caution due to the severe consequences of errors. Research shows these models are vulnerable to adversarial attacks, such as data poisoning and neural trojaning, which can covertly manipulate model behavior, compromising reliability and safety. Current defense strategies like watermarking have limitations: they fail to detect all model modifications and primarily focus on attacks on CNNs in the image domain, neglecting other critical architectures like RNNs. To address these gaps, we introduce DeepiSign-G, a versatile watermarking approach designed for comprehensive verification of leading DNN architectures, including CNNs and RNNs. DeepiSign-G enhances model security by embedding an invisible watermark within the Walsh-Hadamard transform coefficients of the model's parameters. This watermark is highly sensitive and fragile, ensuring prompt detection of any modifications. Unlike traditional hashing techniques, DeepiSign-G allows substantial metadata incorporation directly within the model, enabling detailed, self-contained tracking and verification. We demonstrate DeepiSign-G's applicability across various architectures, including CNN models (VGG, ResNets, DenseNet) and RNNs (Text sentiment classifier). We experiment with four popular datasets: VGG Face, CIFAR10, GTSRB Traffic Sign, and Large Movie Review. We also evaluate DeepiSign-G under five potential attacks. Our comprehensive evaluation confirms that DeepiSign-G effectively detects these attacks without compromising CNN and RNN model performance, highlighting its efficacy as a robust security measure for deep learning applications. Detection of integrity breaches is nearly perfect, while hiding only a bit in approximately 1% of the Walsh-Hadamard coefficients.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑