Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. A victim classifier will predict to an attacker-desired target class whenever a test sample is embedded with the same backdoor pattern (BP) that was used to poison the classifier's training set. Detecting whether a classifier is backdoor attacked is not easy in practice, especially when the defender is, e.g., a downstream user without access to the classifier's training set. This challenge is addressed here by a reverse-engineering defense (RED), which has been shown to yield state-of-the-art performance in several domains. However, existing REDs are not applicable when there are only {\it two classes} or when {\it multiple attacks} are present. These scenarios are first studied in the current paper, under the practical constraints that the defender neither has access to the classifier's training set nor to supervision from clean reference classifiers trained for the same domain. We propose a detection framework based on BP reverse-engineering and a novel {\it expected transferability} (ET) statistic. We show that our ET statistic is effective {\it using the same detection threshold}, irrespective of the classification domain, the attack configuration, and the BP reverse-engineering algorithm that is used. The excellent performance of our method is demonstrated on six benchmark datasets. Notably, our detection framework is also applicable to multi-class scenarios with multiple attacks.
相關內容
A growing body of work has shown that deep neural networks are susceptible to adversarial examples. These take the form of small perturbations applied to the model's input which lead to incorrect predictions. Unfortunately, most literature focuses on visually imperceivable perturbations to be applied to digital images that often are, by design, impossible to be deployed to physical targets. We present Adversarial Scratches: a novel L0 black-box attack, which takes the form of scratches in images, and which possesses much greater deployability than other state-of-the-art attacks. Adversarial Scratches leverage B\'ezier Curves to reduce the dimension of the search space and possibly constrain the attack to a specific location. We test Adversarial Scratches in several scenarios, including a publicly available API and images of traffic signs. Results show that, often, our attack achieves higher fooling rate than other deployable state-of-the-art methods, while requiring significantly fewer queries and modifying very few pixels.
The human footprint is having a unique set of ridges unmatched by any other human being, and therefore it can be used in different identity documents for example birth certificate, Indian biometric identification system AADHAR card, driving license, PAN card, and passport. There are many instances of the crime scene where an accused must walk around and left the footwear impressions as well as barefoot prints and therefore, it is very crucial to recovering the footprints from identifying the criminals. Footprint-based biometric is a considerably newer technique for personal identification. Fingerprints, retina, iris and face recognition are the methods most useful for attendance record of the person. This time the world is facing the problem of global terrorism. It is challenging to identify the terrorist because they are living as regular as the citizens do. Their soft target includes the industries of special interests such as defence, silicon and nanotechnology chip manufacturing units, pharmacy sectors. They pretend themselves as religious persons, so temples and other holy places, even in markets is in their targets. These are the places where one can obtain their footprints quickly. The gait itself is sufficient to predict the behaviour of the suspects. The present research is driven to identify the usefulness of footprint and gait as an alternative to personal identification.
The growing complexity of Cyber-Physical Systems (CPS) and challenges in ensuring safety and security have led to the increasing use of deep learning methods for accurate and scalable anomaly detection. However, machine learning (ML) models often suffer from low performance in predicting unexpected data and are vulnerable to accidental or malicious perturbations. Although robustness testing of deep learning models has been extensively explored in applications such as image classification and speech recognition, less attention has been paid to ML-driven safety monitoring in CPS. This paper presents the preliminary results on evaluating the robustness of ML-based anomaly detection methods in safety-critical CPS against two types of accidental and malicious input perturbations, generated using a Gaussian-based noise model and the Fast Gradient Sign Method (FGSM). We test the hypothesis of whether integrating the domain knowledge (e.g., on unsafe system behavior) with the ML models can improve the robustness of anomaly detection without sacrificing accuracy and transparency. Experimental results with two case studies of Artificial Pancreas Systems (APS) for diabetes management show that ML-based safety monitors trained with domain knowledge can reduce on average up to 54.2% of robustness error and keep the average F1 scores high while improving transparency.
Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning attacks and connect them with old and new algorithms for solving sequential Stackelberg games. By choosing an appropriate loss function for the attacker and optimizing with algorithms that exploit second-order information, we design poisoning attacks that are effective on neural networks. We present efficient implementations that exploit modern auto-differentiation packages and allow simultaneous and coordinated generation of tens of thousands of poisoned points, in contrast to existing methods that generate poisoned points one by one. We further perform extensive experiments that empirically explore the effect of data poisoning attacks on deep neural networks.
Internet of things (IoT) connects all items to the Internet through information-sensing devices to exchange information for intelligent identification and management. Sybil attack is a famous and crippling attack in IoT. Most of the previous methods of detecting Sybil attacks in IoT mainly focus on static IoT while there are very rare methods applicable to mobile IoT. In this paper, a novel, lightweight, and distributive detection scheme based on edge computing is proposed for detecting Sybil attacks in mobile IoT. In the proposed scheme, a detection consists of two rounds. In each round, member nodes are required to send packets to edge nodes. Edge nodes calculate a possible interval of the received signal strength indication (RSSI) from the first round and check whether the RSSI from the second round is in the interval to detect Sybil attack. Extensive experimental studies are included to show that the presented approach outperforms many existing approaches in terms of true detection and false detection rates. Moreover, experimental results show that the fault tolerance design in the proposed approach greatly enhances the detection scheme.
Deep neural networks have become an integral part of our software infrastructure and are being deployed in many widely-used and safety-critical applications. However, their integration into many systems also brings with it the vulnerability to test time attacks in the form of Universal Adversarial Perturbations (UAPs). UAPs are a class of perturbations that when applied to any input causes model misclassification. Although there is an ongoing effort to defend models against these adversarial attacks, it is often difficult to reconcile the trade-offs in model accuracy and robustness to adversarial attacks. Jacobian regularization has been shown to improve the robustness of models against UAPs, whilst model ensembles have been widely adopted to improve both predictive performance and model robustness. In this work, we propose a novel approach, Jacobian Ensembles-a combination of Jacobian regularization and model ensembles to significantly increase the robustness against UAPs whilst maintaining or improving model accuracy. Our results show that Jacobian Ensembles achieves previously unseen levels of accuracy and robustness, greatly improving over previous methods that tend to skew towards only either accuracy or robustness.
The success of deep learning has enabled advances in multimodal tasks that require non-trivial fusion of multiple input domains. Although multimodal models have shown potential in many problems, their increased complexity makes them more vulnerable to attacks. A Backdoor (or Trojan) attack is a class of security vulnerability wherein an attacker embeds a malicious secret behavior into a network (e.g. targeted misclassification) that is activated when an attacker-specified trigger is added to an input. In this work, we show that multimodal networks are vulnerable to a novel type of attack that we refer to as Dual-Key Multimodal Backdoors. This attack exploits the complex fusion mechanisms used by state-of-the-art networks to embed backdoors that are both effective and stealthy. Instead of using a single trigger, the proposed attack embeds a trigger in each of the input modalities and activates the malicious behavior only when both the triggers are present. We present an extensive study of multimodal backdoors on the Visual Question Answering (VQA) task with multiple architectures and visual feature backbones. A major challenge in embedding backdoors in VQA models is that most models use visual features extracted from a fixed pretrained object detector. This is challenging for the attacker as the detector can distort or ignore the visual trigger entirely, which leads to models where backdoors are over-reliant on the language trigger. We tackle this problem by proposing a visual trigger optimization strategy designed for pretrained object detectors. Through this method, we create Dual-Key Backdoors with over a 98% attack success rate while only poisoning 1% of the training data. Finally, we release TrojVQA, a large collection of clean and trojan VQA models to enable research in defending against multimodal backdoors.
Distributed machine learning (ML) can bring more computational resources to bear than single-machine learning, thus enabling reductions in training time. Distributed learning partitions models and data over many machines, allowing model and dataset sizes beyond the available compute power and memory of a single machine. In practice though, distributed ML is challenging when distribution is mandatory, rather than chosen by the practitioner. In such scenarios, data could unavoidably be separated among workers due to limited memory capacity per worker or even because of data privacy issues. There, existing distributed methods will utterly fail due to dominant transfer costs across workers, or do not even apply. We propose a new approach to distributed fully connected neural network learning, called independent subnet training (IST), to handle these cases. In IST, the original network is decomposed into a set of narrow subnetworks with the same depth. These subnetworks are then trained locally before parameters are exchanged to produce new subnets and the training cycle repeats. Such a naturally "model parallel" approach limits memory usage by storing only a portion of network parameters on each device. Additionally, no requirements exist for sharing data between workers (i.e., subnet training is local and independent) and communication volume and frequency are reduced by decomposing the original network into independent subnets. These properties of IST can cope with issues due to distributed data, slow interconnects, or limited device memory, making IST a suitable approach for cases of mandatory distribution. We show experimentally that IST results in training times that are much lower than common distributed learning approaches.
Backdoor attacks insert malicious data into a training set so that, during inference time, it misclassifies inputs that have been patched with a backdoor trigger as the malware specified label. For backdoor attacks to bypass human inspection, it is essential that the injected data appear to be correctly labeled. The attacks with such property are often referred to as "clean-label attacks." Existing clean-label backdoor attacks require knowledge of the entire training set to be effective. Obtaining such knowledge is difficult or impossible because training data are often gathered from multiple sources (e.g., face images from different users). It remains a question whether backdoor attacks still present a real threat. This paper provides an affirmative answer to this question by designing an algorithm to mount clean-label backdoor attacks based only on the knowledge of representative examples from the target class. With poisoning equal to or less than 0.5% of the target-class data and 0.05% of the training set, we can train a model to classify test examples from arbitrary classes into the target class when the examples are patched with a backdoor trigger. Our attack works well across datasets and models, even when the trigger presents in the physical world. We explore the space of defenses and find that, surprisingly, our attack can evade the latest state-of-the-art defenses in their vanilla form, or after a simple twist, we can adapt to the downstream defenses. We study the cause of the intriguing effectiveness and find that because the trigger synthesized by our attack contains features as persistent as the original semantic features of the target class, any attempt to remove such triggers would inevitably hurt the model accuracy first.
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger. Backdoor attack could happen when the training process is not fully controlled by the user, such as training on third-party datasets or adopting third-party models, which poses a new and realistic threat. Although backdoor learning is an emerging and rapidly growing research area, its systematic review, however, remains blank. In this paper, we present the first comprehensive survey of this realm. We summarize and categorize existing backdoor attacks and defenses based on their characteristics, and provide a unified framework for analyzing poisoning-based backdoor attacks. Besides, we also analyze the relation between backdoor attacks and the relevant fields ($i.e.,$ adversarial attack and data poisoning), and summarize the benchmark datasets. Finally, we briefly outline certain future research directions relying upon reviewed works.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191