اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدUniversal Litmus Patterns: Revealing Backdoor Attacks in CNNs
44
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
The unprecedented success of deep neural networks in many applications has made these networks a prime target for adversarial exploitation. In this paper, we introduce a benchmark technique for detecting backdoor attacks (aka Trojan attacks) on deep convolutional neural networks (CNNs). We introduce the concept of Universal Litmus Patterns (ULPs), which enable one to reveal backdoor attacks by feeding these universal patterns to the network and analyzing the output (i.e., classifying the network as `clean or `corrupted). This detection is fast because it requires only a few forward passes through a CNN. We demonstrate the effectiveness of ULPs for detecting backdoor attacks on thousands of networks with different architectures trained on four benchmark datasets, namely the German Traffic Sign Recognition Benchmark (GTSRB), MNIST, CIFAR10, and Tiny-ImageNet. The codes and train/test models for this paper can be found here https://umbcvision.github.io/Universal-Litmus-Patterns/.
قيم البحث
اقرأ أيضاً
Large-scale unlabeled data has allowed recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (MoCo and BYOL) use an inductive bias
that different augmentations (e.g. random crops) of an image should produce similar embeddings. We show that such methods are vulnerable to backdoor attacks where an attacker poisons a part of the unlabeled data by adding a small trigger (known to the attacker) to the images. The model performance is good on clean test images but the attacker can manipulate the decision of the model by showing the trigger at test time. Backdoor attacks have been studied extensively in supervised learning and to the best of our knowledge, we are the first to study them for self-supervised learning. Backdoor attacks are more practical in self-supervised learning since the unlabeled data is large and as a result, an inspection of the data to avoid the presence of poisoned data is prohibitive. We show that in our targeted attack, the attacker can produce many false positives for the target category by using the trigger at test time. We also propose a knowledge distillation based defense algorithm that succeeds in neutralizing the attack. Our code is available here: https://github.com/UMBCvision/SSL-Backdoor .
Despite the success of convolutional neural networks (CNNs) in many computer vision and image analysis tasks, they remain vulnerable against so-called adversarial attacks: Small, crafted perturbations in the input images can lead to false predictions
. A possible defense is to detect adversarial examples. In this work, we show how analysis in the Fourier domain of input images and feature maps can be used to distinguish benign test samples from adversarial images. We propose two novel detection methods: Our first method employs the magnitude spectrum of the input images to detect an adversarial attack. This simple and robust classifier can successfully detect adversarial perturbations of three commonly used attack methods. The second method builds upon the first and additionally extracts the phase of Fourier coefficients of feature-maps at different layers of the network. With this extension, we are able to improve adversarial detection rates compared to state-of-the-art detectors on five different attack methods.
Researchers have shown that the predictions of a convolutional neural network (CNN) for an image set can be severely distorted by one single image-agnostic perturbation, or universal perturbation, usually with an empirically fixed threshold in the sp
atial domain to restrict its perceivability. However, by considering the human perception, we propose to adopt JND thresholds to guide the perceivability of universal adversarial perturbations. Based on this, we propose a frequency-tuned universal attack method to compute universal perturbations and show that our method can realize a good balance between perceivability and effectiveness in terms of fooling rate by adapting the perturbations to the local frequency content. Compared with existing universal adversarial attack techniques, our frequency-tuned attack method can achieve cutting-edge quantitative results. We demonstrate that our approach can significantly improve the performance of the baseline on both white-box and black-box attacks.
Pre-trained models (PTMs) have been widely used in various downstream tasks. The parameters of PTMs are distributed on the Internet and may suffer backdoor attacks. In this work, we demonstrate the universal vulnerability of PTMs, where fine-tuned PT
Ms can be easily controlled by backdoor attacks in arbitrary downstream tasks. Specifically, attackers can add a simple pre-training task, which restricts the output representations of trigger instances to pre-defined vectors, namely neuron-level backdoor attack (NeuBA). If the backdoor functionality is not eliminated during fine-tuning, the triggers can make the fine-tuned model predict fixed labels by pre-defined vectors. In the experiments of both natural language processing (NLP) and computer vision (CV), we show that NeuBA absolutely controls the predictions for trigger instances without any knowledge of downstream tasks. Finally, we apply several defense methods to NeuBA and find that model pruning is a promising direction to resist NeuBA by excluding backdoored neurons. Our findings sound a red alarm for the wide use of PTMs. Our source code and models are available at url{https://github.com/thunlp/NeuBA}.
Deep learning models have recently shown to be vulnerable to backdoor poisoning, an insidious attack where the victim model predicts clean images correctly but classifies the same images as the target class when a trigger poison pattern is added. Thi
s poison pattern can be embedded in the training dataset by the adversary. Existing defenses are effective under certain conditions such as a small size of the poison pattern, knowledge about the ratio of poisoned training samples or when a validated clean dataset is available. Since a defender may not have such prior knowledge or resources, we propose a defense against backdoor poisoning that is effective even when those prerequisites are not met. It is made up of several parts: one to extract a backdoor poison signal, detect poison target and base classes, and filter out poisoned from clean samples with proven guarantees. The final part of our defense involves retraining the poisoned model on a dataset augmented with the extracted poison signal and corrective relabeling of poisoned samples to neutralize the backdoor. Our approach has shown to be effective in defending against backdoor attacks that use both small and large-sized poison patterns on nine different target-base class pairs from the CIFAR10 dataset.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
