Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly focus on digital attacks that use digitally generated patterns as triggers. A critical question remains unanswered: can backdoor attacks succeed using physical objects as triggers, thus making them a credible threat against deep learning systems in the real world? We conduct a detailed empirical study to explore this question for facial recognition, a critical deep learning task. Using seven physical objects as triggers, we collect a custom dataset of 3205 images of ten volunteers and use it to study the feasibility of physical backdoor attacks under a variety of real-world conditions. Our study reveals two key findings. First, physical backdoor attacks can be highly successful if they are carefully configured to overcome the constraints imposed by physical objects. In particular, the placement of successful triggers is largely constrained by the target model's dependence on key facial features. Second, four of today's state-of-the-art defenses against (digital) backdoors are ineffective against physical backdoors, because the use of physical objects breaks core assumptions used to construct these defenses. Our study confirms that (physical) backdoor attacks are not a hypothetical phenomenon but rather pose a serious real-world threat to critical classification tasks. We need new and more robust defenses against backdoors in the physical world.
相關內容
Research in automatic speaker recognition (SR) has been undertaken for several decades, reaching great performance. However, researchers discovered potential loopholes in these technologies like spoofing attacks. Quite recently, a new genre of attack, termed adversarial attacks, has been proved to be fatal in computer vision and it is vital to study their effects on SR systems. This paper examines how state-of-the-art speaker identification (SID) systems are vulnerable to adversarial attacks and how to defend against them. We investigated adversarial attacks common in the literature like fast gradient sign method (FGSM), iterative-FGSM / basic iterative method (BIM) and Carlini-Wagner (CW). Furthermore, we propose four pre-processing defenses against these attacks - randomized smoothing, DefenseGAN, variational autoencoder (VAE) and WaveGAN vocoder. We found that SID is extremely vulnerable under Iterative FGSM and CW attacks. Randomized smoothing defense robustified the system for imperceptible BIM and CW attacks recovering classification accuracies ~97%. Defenses based on generative models (DefenseGAN, VAE and WaveGAN) project adversarial examples (outside manifold) back into the clean manifold. In the case that attacker cannot adapt the attack to the defense (black-box defense), WaveGAN performed the best, being close to clean condition (Accuracy>97%). However, if the attack is adapted to the defense - assuming the attacker has access to the defense model (white-box defense), VAE and WaveGAN protection dropped significantly-50% and 37% accuracy for CW attack. To counteract this,we combined randomized smoothing with VAE or WaveGAN. We found that smoothing followed by WaveGAN vocoder was the most effective defense overall. As a black-box defense, it provides 93% average accuracy. As white-box defense, accuracy only degraded for iterative attacks with perceptible perturbations (L>=0.01).
Recently, a number of backdoor attacks against Federated Learning (FL) have been proposed. In such attacks, an adversary injects poisoned model updates into the federated model aggregation process with the goal of manipulating the aggregated model to provide false predictions on specific adversary-chosen inputs. A number of defenses have been proposed; but none of them can effectively protect the FL process also against so-called multi-backdoor attacks in which multiple different backdoors are injected by the adversary simultaneously without severely impacting the benign performance of the aggregated model. To overcome this challenge, we introduce FLGUARD, a poisoning defense framework that is able to defend FL against state-of-the-art backdoor attacks while simultaneously maintaining the benign performance of the aggregated model. Moreover, FL is also vulnerable to inference attacks, in which a malicious aggregator can infer information about clients' training data from their model updates. To thwart such attacks, we augment FLGUARD with state-of-the-art secure computation techniques that securely evaluate the FLGUARD algorithm. We provide formal argumentation for the effectiveness of our FLGUARD and extensively evaluate it against known backdoor attacks on several datasets and applications (including image classification, word prediction, and IoT intrusion detection), demonstrating that FLGUARD can entirely remove backdoors with a negligible effect on accuracy. We also show that private FLGUARD achieves practical runtimes.
We investigate the security of Split Learning---a novel collaborative machine learning framework that enables peak performance by requiring minimal resources consumption. In the present paper, we expose vulnerabilities of the protocol and demonstrate its inherent insecurity by introducing general attack strategies targeting the reconstruction of clients' private training sets. More prominently, we show that a malicious server can actively hijack the learning process of the distributed model and bring it into an insecure state that enables inference attacks on clients' data. We implement different adaptations of the attack and test them on various datasets as well as within realistic threat scenarios. We demonstrate that our attack is able to overcome recently proposed defensive techniques aimed at enhancing the security of the split learning protocol. Finally, we also illustrate the protocol's insecurity against malicious clients by extending previously devised attacks for Federated Learning. To make our results reproducible, we made our code available at //github.com/pasquini-dario/SplitNN_FSHA.
During the last two decades, distributed energy systems, especially renewable energy sources (RES), have become more economically viable with increasing market share and penetration levels on power systems. In addition to decarbonization and decentralization of energy systems, digitalization has also become very important. The use of artificial intelligence (AI), advanced optimization algorithms, Industrial Internet of Things (IIoT), and other digitalization frameworks makes modern power system assets more intelligent, while vulnerable to cybersecurity risks. This paper proposes the concept of the Internet of Predictable Things (IoPT) that incorporates advanced data analytics and machine learning methods to increase the resiliency of cyber-physical systems against cybersecurity risks. The proposed concept is demonstrated using a cyber-physical system testbed under a variety of cyber attack scenarios as a proof of concept (PoC).
As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden backdoors. The so-called backdoor attacks are especially difficult to detect since the model behaves normally on standard test data but gives wrong outputs when triggered by certain backdoor keys. Although Byzantine-tolerant training algorithms provide convergence guarantee, provable defense against backdoor attacks remains largely unsolved. Methods based on randomized smoothing can only correct a small number of corrupted pixels or labels; methods based on subset aggregation cause a severe drop in classification accuracy due to low data utilization. We propose a novel framework that generalizes existing subset aggregation methods. The framework shows that the subset selection process, a deciding factor for subset aggregation methods, can be viewed as a code design problem. We derive the theoretical bound of data utilization ratio and provide optimal code construction. Experiments on non-IID versions of MNIST and CIFAR-10 show that our method with optimal codes significantly outperforms baselines using non-overlapping partition and random selection. Additionally, integration with existing coding theory results shows that special codes can track the location of the attackers. Such capability provides new countermeasures to backdoor attacks.
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.
Deep learning models on graphs have achieved remarkable performance in various graph analysis tasks, e.g., node classification, link prediction and graph clustering. However, they expose uncertainty and unreliability against the well-designed inputs, i.e., adversarial examples. Accordingly, various studies have emerged for both attack and defense addressed in different graph analysis tasks, leading to the arms race in graph adversarial learning. For instance, the attacker has poisoning and evasion attack, and the defense group correspondingly has preprocessing- and adversarial- based methods. Despite the booming works, there still lacks a unified problem definition and a comprehensive review. To bridge this gap, we investigate and summarize the existing works on graph adversarial learning tasks systemically. Specifically, we survey and unify the existing works w.r.t. attack and defense in graph analysis tasks, and give proper definitions and taxonomies at the same time. Besides, we emphasize the importance of related evaluation metrics, and investigate and summarize them comprehensively. Hopefully, our works can serve as a reference for the relevant researchers, thus providing assistance for their studies. More details of our works are available at //github.com/gitgiter/Graph-Adversarial-Learning.
There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack. We present a new approach towards ending this cycle where we "deflect'' adversarial attacks by causing the attacker to produce an input that semantically resembles the attack's target class. To this end, we first propose a stronger defense based on Capsule Networks that combines three detection mechanisms to achieve state-of-the-art detection performance on both standard and defense-aware attacks. We then show that undetected attacks against our defense often perceptually resemble the adversarial target class by performing a human study where participants are asked to label images produced by the attack. These attack images can no longer be called "adversarial'' because our network classifies them the same way as humans do.
Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions. Recent studies show that adversarial examples can pose a threat to real-world security-critical applications: a "physical adversarial Stop Sign" can be synthesized such that the autonomous driving cars will misrecognize it as others (e.g., a speed limit sign). However, these image-space adversarial examples cannot easily alter 3D scans of widely equipped LiDAR or radar on autonomous vehicles. In this paper, we reveal the potential vulnerabilities of LiDAR-based autonomous driving detection systems, by proposing an optimization based approach LiDAR-Adv to generate adversarial objects that can evade the LiDAR-based detection system under various conditions. We first show the vulnerabilities using a blackbox evolution-based algorithm, and then explore how much a strong adversary can do, using our gradient-based approach LiDAR-Adv. We test the generated adversarial objects on the Baidu Apollo autonomous driving platform and show that such physical systems are indeed vulnerable to the proposed attacks. We also 3D-print our adversarial objects and perform physical experiments to illustrate that such vulnerability exists in the real world. Please find more visualizations and results on the anonymous website: //sites.google.com/view/lidar-adv.
Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the so-called false positives), obscuring alerts resulting from actual malicious activity. While numerous methods for reducing the scope of this issue have been proposed, ultimately one must still decide how to prioritize which alerts to investigate, and most existing prioritization methods are heuristic, for example, based on suspiciousness or priority scores. We introduce a novel approach for computing a policy for prioritizing alerts using adversarial reinforcement learning. Our approach assumes that the attackers know the full state of the detection system and dynamically choose an optimal attack as a function of this state, as well as of the alert prioritization policy. The first step of our approach is to capture the interaction between the defender and attacker in a game theoretic model. To tackle the computational complexity of solving this game to obtain a dynamic stochastic alert prioritization policy, we propose an adversarial reinforcement learning framework. In this framework, we use neural reinforcement learning to compute best response policies for both the defender and the adversary to an arbitrary stochastic policy of the other. We then use these in a double-oracle framework to obtain an approximate equilibrium of the game, which in turn yields a robust stochastic policy for the defender. Extensive experiments using case studies in fraud and intrusion detection demonstrate that our approach is effective in creating robust alert prioritization policies.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191