ترغب بنشر مسار تعليمي؟ اضغط هنا

Evaluating the Robustness of Trigger Set-Based Watermarks Embedded in Deep Neural Networks

73   0   0.0 ( 0 )
 نشر من قبل Suyoung Lee
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Trigger set-based watermarking schemes have gained emerging attention as they provide a means to prove ownership for deep neural network model owners. In this paper, we argue that state-of-the-art trigger set-based watermarking algorithms do not achieve their designed goal of proving ownership. We posit that this impaired capability stems from two common experimental flaws that the existing research practice has committed when evaluating the robustness of watermarking algorithms: (1) incomplete adversarial evaluation and (2) overlooked adaptive attacks. We conduct a comprehensive adversarial evaluation of 10 representative watermarking schemes against six of the existing attacks and demonstrate that each of these watermarking schemes lacks robustness against at least two attacks. We also propose novel adaptive attacks that harness the adversarys knowledge of the underlying watermarking algorithm of a target model. We demonstrate that the proposed attacks effectively break all of the 10 watermarking schemes, consequently allowing adversaries to obscure the ownership of any watermarked model. We encourage follow-up studies to consider our guidelines when evaluating the robustness of their watermarking schemes via conducting comprehensive adversarial evaluation that include our adaptive attacks to demonstrate a meaningful upper bound of watermark robustness.



قيم البحث

اقرأ أيضاً

As companies continue to invest heavily in larger, more accurate and more robust deep learning models, they are exploring approaches to monetize their models while protecting their intellectual property. Model licensing is promising, but requires a r obust tool for owners to claim ownership of models, i.e. a watermark. Unfortunately, current designs have not been able to address piracy attacks, where third parties falsely claim model ownership by embedding their own pirate watermarks into an already-watermarked model. We observe that resistance to piracy attacks is fundamentally at odds with the current use of incremental training to embed watermarks into models. In this work, we propose null embedding, a new way to build piracy-resistant watermarks into DNNs that can only take place at a models initial training. A null embedding takes a bit string (watermark value) as input, and builds strong dependencies between the models normal classification accuracy and the watermark. As a result, attackers cannot remove an embedded watermark via tuning or incremental training, and cannot add new pirate watermarks to already watermarked models. We empirically show that our proposed watermarks achieve piracy resistance and other watermark properties, over a wide range of tasks and models. Finally, we explore a number of adaptive counter-measures, and show our watermark remains robust against a variety of model modifications, including model fine-tuning, compression, and existing methods to detect/remove backdoors. Our watermarked models are also amenable to transfer learning without losing their watermark properties.
Creating a state-of-the-art deep-learning system requires vast amounts of data, expertise, and hardware, yet research into embedding copyright protection for neural networks has been limited. One of the main methods for achieving such protection invo lves relying on the susceptibility of neural networks to backdoor attacks, but the robustness of these tactics has been primarily evaluated against pruning, fine-tuning, and model inversion attacks. In this work, we propose a neural network laundering algorithm to remove black-box backdoor watermarks from neural networks even when the adversary has no prior knowledge of the structure of the watermark. We are able to effectively remove watermarks used for recent defense or copyright protection mechanisms while achieving test accuracies above 97% and 80% for both MNIST and CIFAR-10, respectively. For all backdoor watermarking methods addressed in this paper, we find that the robustness of the watermark is significantly weaker than the original claims. We also demonstrate the feasibility of our algorithm in more complex tasks as well as in more realistic scenarios where the adversary is able to carry out efficient laundering attacks using less than 1% of the original training set size, demonstrating that existing backdoor watermarks are not sufficient to reach their claims.
Deep neural networks are vulnerable to adversarial examples. Prior defenses attempted to make deep networks more robust by either changing the network architecture or augmenting the training set with adversarial examples, but both have inherent limit ations. Motivated by recent research that shows outliers in the training set have a high negative influence on the trained model, we studied the relationship between model robustness and the quality of the training set. We first show that outliers give the model better generalization ability but weaker robustness. Next, we propose an adversarial example detection framework, in which we design two methods for removing outliers from training set to obtain the sanitized model and then detect adversarial example by calculating the difference of outputs between the original and the sanitized model. We evaluated the framework on both MNIST and SVHN. Based on the difference measured by Kullback-Leibler divergence, we could detect adversarial examples with accuracy between 94.67% to 99.89%.
98 - Shuhan Yuan , Xintao Wu , Jun Li 2017
In this paper, we focus on fraud detection on a signed graph with only a small set of labeled training data. We propose a novel framework that combines deep neural networks and spectral graph analysis. In particular, we use the node projection (calle d as spectral coordinate) in the low dimensional spectral space of the graphs adjacency matrix as input of deep neural networks. Spectral coordinates in the spectral space capture the most useful topology information of the network. Due to the small dimension of spectral coordinates (compared with the dimension of the adjacency matrix derived from a graph), training deep neural networks becomes feasible. We develop and evaluate two neural networks, deep autoencoder and convolutional neural network, in our fraud detection framework. Experimental results on a real signed graph show that our spectrum based deep neural networks are effective in fraud detection.
Machine learning (ML), especially deep learning (DL) techniques have been increasingly used in anomaly-based network intrusion detection systems (NIDS). However, ML/DL has shown to be extremely vulnerable to adversarial attacks, especially in such se curity-sensitive systems. Many adversarial attacks have been proposed to evaluate the robustness of ML-based NIDSs. Unfortunately, existing attacks mostly focused on feature-space and/or white-box attacks, which make impractical assumptions in real-world scenarios, leaving the study on practical gray/black-box attacks largely unexplored. To bridge this gap, we conduct the first systematic study of the gray/black-box traffic-space adversarial attacks to evaluate the robustness of ML-based NIDSs. Our work outperforms previous ones in the following aspects: (i) practical-the proposed attack can automatically mutate original traffic with extremely limited knowledge and affordable overhead while preserving its functionality; (ii) generic-the proposed attack is effective for evaluating the robustness of various NIDSs using diverse ML/DL models and non-payload-based features; (iii) explainable-we propose an explanation method for the fragile robustness of ML-based NIDSs. Based on this, we also propose a defense scheme against adversarial attacks to improve system robustness. We extensively evaluate the robustness of various NIDSs using diverse feature sets and ML/DL models. Experimental results show our attack is effective (e.g., >97% evasion rate in half cases for Kitsune, a state-of-the-art NIDS) with affordable execution cost and the proposed defense method can effectively mitigate such attacks (evasion rate is reduced by >50% in most cases).

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا