اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدCheck Your Other Door! Establishing Backdoor Attacks in the Frequency Domain
505
0
0.0
(
0
)
نشر من قبل
Hasan Abed Al Kader Hammoud
تاريخ النشر
2021
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Deep Neural Networks (DNNs) have been utilized in various applications ranging from image classification and facial recognition to medical imagery analysis and real-time object detection. As our models become more sophisticated and complex, the computational cost of training such models becomes a burden for small companies and individuals; for this reason, outsourcing the training process has been the go-to option for such users. Unfortunately, outsourcing the training process comes at the cost of vulnerability to backdoor attacks. These attacks aim at establishing hidden backdoors in the DNN such that the model performs well on benign samples but outputs a particular target label when a trigger is applied to the input. Current backdoor attacks rely on generating triggers in the image/pixel domain; however, as we show in this paper, it is not the only domain to exploit and one should always check the other doors. In this work, we propose a complete pipeline for generating a dynamic, efficient, and invisible backdoor attack in the frequency domain. We show the advantages of utilizing the frequency domain for establishing undetectable and powerful backdoor attacks through extensive experiments on various datasets and network architectures. The backdoored models are shown to break various state-of-the-art defences. We also show two possible defences that succeed against frequency-based backdoor attacks and possible ways for the attacker to bypass them. We conclude the work with some remarks regarding a networks learning capacity and the capability of embedding a backdoor attack in the model.
قيم البحث
اقرأ أيضاً
This work provides the community with a timely comprehensive review of backdoor attacks and countermeasures on deep learning. According to the attackers capability and affected stage of the machine learning pipeline, the attack surfaces are recognize
d to be wide and then formalized into six categorizations: code poisoning, outsourcing, pretrained, data collection, collaborative learning and post-deployment. Accordingly, attacks under each categorization are combed. The countermeasures are categorized into four general classes: blind backdoor removal, offline backdoor inspection, online backdoor inspection, and post backdoor removal. Accordingly, we review countermeasures, and compare and analyze their advantages and disadvantages. We have also reviewed the flip side of backdoor attacks, which are explored for i) protecting intellectual property of deep learning models, ii) acting as a honeypot to catch adversarial example attacks, and iii) verifying data deletion requested by the data contributor.Overall, the research on defense is far behind the attack, and there is no single defense that can prevent all types of backdoor attacks. In some cases, an attacker can intelligently bypass existing defenses with an adaptive attack. Drawing the insights from the systematic review, we also present key areas for future research on the backdoor, such as empirical security evaluations from physical trigger attacks, and in particular, more efficient and practical countermeasures are solicited.
Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing unexpected behav
ior. In this paper, we create covert and scattered triggers for backdoor attacks, invisible backdoors, where triggers can fool both DNN models and human inspection. We apply our invisible backdoors through two state-of-the-art methods of embedding triggers for backdoor attacks. The first approach on Badnets embeds the trigger into DNNs through steganography. The second approach of a trojan attack uses two types of additional regularization terms to generate the triggers with irregular shape and size. We use the Attack Success Rate and Functionality to measure the performance of our attacks. We introduce two novel definitions of invisibility for human perception; one is conceptualized by the Perceptual Adversarial Similarity Score (PASS) and the other is Learned Perceptual Image Patch Similarity (LPIPS). We show that the proposed invisible backdoors can be fairly effective across various DNN models as well as four datasets MNIST, CIFAR-10, CIFAR-100, and GTSRB, by measuring their attack success rates for the adversary, functionality for the normal users, and invisibility scores for the administrators. We finally argue that the proposed invisible backdoor attacks can effectively thwart the state-of-the-art trojan backdoor detection approaches, such as Neural Cleanse and TABOR.
Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments. A malicious backdoor could be embedded in a model by poisoning the training dataset, whose intention is to make the infect
ed model give wrong predictions during inference when the specific trigger appears. To mitigate the potential threats of backdoor attacks, various backdoor detection and defense methods have been proposed. However, the existing techniques usually require the poisoned training data or access to the white-box model, which is commonly unavailable in practice. In this paper, we propose a black-box backdoor detection (B3D) method to identify backdoor attacks with only query access to the model. We introduce a gradient-free optimization algorithm to reverse-engineer the potential trigger for each class, which helps to reveal the existence of backdoor attacks. In addition to backdoor detection, we also propose a simple strategy for reliable predictions using the identified backdoored models. Extensive experiments on hundreds of DNN models trained on several datasets corroborate the effectiveness of our method under the black-box setting against various backdoor attacks.
Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger, while it performs
well on benign samples. Currently, most of existing backdoor attacks adopted the setting of emph{static} trigger, $i.e.,$ triggers across the training and testing images follow the same appearance and are located in the same area. In this paper, we revisit this attack paradigm by analyzing the characteristics of the static trigger. We demonstrate that such an attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training. We further explore how to utilize this property for backdoor defense, and discuss how to alleviate such vulnerability of existing attacks.
Related-domain attackers control a sibling domain of their target web application, e.g., as the result of a subdomain takeover. Despite their additional power over traditional web attackers, related-domain attackers received only limited attention by
the research community. In this paper we define and quantify for the first time the threats that related-domain attackers pose to web application security. In particular, we first clarify the capabilities that related-domain attackers can acquire through different attack vectors, showing that different instances of the related-domain attacker concept are worth attention. We then study how these capabilities can be abused to compromise web application security by focusing on different angles, including: cookies, CSP, CORS, postMessage and domain relaxation. By building on this framework, we report on a large-scale security measurement on the top 50k domains from the Tranco list that led to the discovery of vulnerabilities in 887 sites, where we quantified the threats posed by related-domain attackers to popular web applications.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
