اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدRemoving Backdoor-Based Watermarks in Neural Networks with Limited Data
83
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Deep neural networks have been widely applied and achieved great success in various fields. As training deep models usually consumes massive data and computational resources, trading the trained deep models is highly demanded and lucrative nowadays. Unfortunately, the naive trading schemes typically involves potential risks related to copyright and trustworthiness issues, e.g., a sold model can be illegally resold to others without further authorization to reap huge profits. To tackle this problem, various watermarking techniques are proposed to protect the model intellectual property, amongst which the backdoor-based watermarking is the most commonly-used one. However, the robustness of these watermarking approaches is not well evaluated under realistic settings, such as limited in-distribution data availability and agnostic of watermarking patterns. In this paper, we benchmark the robustness of watermarking, and propose a novel backdoor-based watermark removal framework using limited data, dubbed WILD. The proposed WILD removes the watermarks of deep models with only a small portion of training data, and the output model can perform the same as models trained from scratch without watermarks injected. In particular, a novel data augmentation method is utilized to mimic the behavior of watermark triggers. Combining with the distribution alignment between the normal and perturbed (e.g., occluded) data in the feature space, our approach generalizes well on all typical types of trigger contents. The experimental results demonstrate that our approach can effectively remove the watermarks without compromising the deep model performance for the original task with the limited access to training data.
قيم البحث
اقرأ أيضاً
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.
Recent studies have shown that DNNs can be compromised by backdoor attacks crafted at training time. A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data. At test tim
e, the victim model behaves normally on clean test data, yet consistently predicts a specific (likely incorrect) target class whenever the backdoor pattern is present in a test example. While existing backdoor attacks are effective, they are not stealthy. The modifications made on training data or labels are often suspicious and can be easily detected by simple data filtering or human inspection. In this paper, we present a new type of backdoor attack inspired by an important natural phenomenon: reflection. Using mathematical modeling of physical reflection models, we propose reflection backdoor (Refool) to plant reflections as backdoor into a victim model. We demonstrate on 3 computer vision tasks and 5 datasets that, Refool can attack state-of-the-art DNNs with high success rate, and is resistant to state-of-the-art backdoor defenses.
Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limi
ted data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5.59 to 2.42.
Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already numerous wo
rks on backdoor attacks on neural networks, but only a few works consider graph neural networks (GNNs). As such, there is no intensive research on explaining the impact of trigger injecting position on the performance of backdoor attacks on GNNs. To bridge this gap, we conduct an experimental investigation on the performance of backdoor attacks on GNNs. We apply two powerful GNN explainability approaches to select the optimal trigger injecting position to achieve two attacker objectives -- high attack success rate and low clean accuracy drop. Our empirical results on benchmark datasets and state-of-the-art neural network models demonstrate the proposed methods effectiveness in selecting trigger injecting position for backdoor attacks on GNNs. For instance, on the node classification task, the backdoor attack with trigger injecting position selected by GraphLIME reaches over $84 %$ attack success rate with less than $2.5 %$ accuracy drop
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.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
