Targeted model poisoning attacks pose a significant threat to federated learning systems. Recent studies show that edge-case targeted attacks, which target a small fraction of the input space are nearly impossible to counter using existing fixed defense strategies. In this paper, we strive to design a learned-defense strategy against such attacks, using a small defense dataset. The defense dataset can be collected by the central authority of the federated learning task, and should contain a mix of poisoned and clean examples. The proposed framework, LearnDefend, estimates the probability of a client update being malicious. The examples in defense dataset need not be pre-marked as poisoned or clean. We also learn a poisoned data detector model which can be used to mark each example in the defense dataset as clean or poisoned. We estimate the poisoned data detector and the client importance models in a coupled optimization approach. Our experiments demonstrate that LearnDefend is capable of defending against state-of-the-art attacks where existing fixed defense strategies fail. We also show that LearnDefend is robust to size and noise in the marking of clean examples in the defense dataset.
相關內容
The robustness of modern machine learning (ML) models has become an increasing concern within the community. The ability to subvert a model into making errant predictions using seemingly inconsequential changes to input is startling, as is our lack of success in building models robust to this concern. Existing research shows progress, but current mitigations come with a high cost and simultaneously reduce the model's accuracy. However, such trade-offs may not be necessary when other design choices could subvert the risk. In this survey we review the current literature on attacks and their real-world occurrences, or limited evidence thereof, to critically evaluate the real-world risks of adversarial machine learning (AML) for the average entity. This is done with an eye toward how one would then mitigate these attacks in practice, the risks for production deployment, and how those risks could be managed. In doing so we elucidate that many AML threats do not warrant the cost and trade-offs of robustness due to a low likelihood of attack or availability of superior non-ML mitigations. Our analysis also recommends cases where an actor should be concerned about AML to the degree where robust ML models are necessary for a complete deployment.
Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. However, many concerns regarding client-side detectability of MS attacks were raised, questioning their practicality once they are publicly known. In this work, for the first time, we thoroughly study the problem of client-side detectability.We demonstrate that most prior MS attacks, which fundamentally rely on one of two key principles, are detectable by principled client-side checks. Further, we formulate desiderata for practical MS attacks and propose SEER, a novel attack framework that satisfies all desiderata, while stealing user data from gradients of realistic networks, even for large batch sizes (up to 512 in our experiments) and under secure aggregation. The key insight of SEER is the use of a secret decoder, which is jointly trained with the shared model. Our work represents a promising first step towards more principled treatment of MS attacks, paving the way for realistic data stealing that can compromise user privacy in real-world deployments.
Malware detectors based on machine learning (ML) have been shown to be susceptible to adversarial malware examples. However, current methods to generate adversarial malware examples still have their limits. They either rely on detailed model information (gradient-based attacks), or on detailed outputs of the model - such as class probabilities (score-based attacks), neither of which are available in real-world scenarios. Alternatively, adversarial examples might be crafted using only the label assigned by the detector (label-based attack) to train a substitute network or an agent using reinforcement learning. Nonetheless, label-based attacks might require querying a black-box system from a small number to thousands of times, depending on the approach, which might not be feasible against malware detectors. This work presents a novel query-free approach to craft adversarial malware examples to evade ML-based malware detectors. To this end, we have devised a GAN-based framework to generate adversarial malware examples that look similar to benign executables in the feature space. To demonstrate the suitability of our approach we have applied the GAN-based attack to three common types of features usually employed by static ML-based malware detectors: (1) Byte histogram features, (2) API-based features, and (3) String-based features. Results show that our model-agnostic approach performs on par with MalGAN, while generating more realistic adversarial malware examples without requiring any query to the malware detectors. Furthermore, we have tested the generated adversarial examples against state-of-the-art multimodal and deep learning malware detectors, showing a decrease in detection performance, as well as a decrease in the average number of detections by the anti-malware engines in VirusTotal.
Mis- and disinformation are a substantial global threat to our security and safety. To cope with the scale of online misinformation, researchers have been working on automating fact-checking by retrieving and verifying against relevant evidence. However, despite many advances, a comprehensive evaluation of the possible attack vectors against such systems is still lacking. Particularly, the automated fact-verification process might be vulnerable to the exact disinformation campaigns it is trying to combat. In this work, we assume an adversary that automatically tampers with the online evidence in order to disrupt the fact-checking model via camouflaging the relevant evidence or planting a misleading one. We first propose an exploratory taxonomy that spans these two targets and the different threat model dimensions. Guided by this, we design and propose several potential attack methods. We show that it is possible to subtly modify claim-salient snippets in the evidence and generate diverse and claim-aligned evidence. Thus, we highly degrade the fact-checking performance under many different permutations of the taxonomy's dimensions. The attacks are also robust against post-hoc modifications of the claim. Our analysis further hints at potential limitations in models' inference when faced with contradicting evidence. We emphasize that these attacks can have harmful implications on the inspectable and human-in-the-loop usage scenarios of such models, and we conclude by discussing challenges and directions for future defenses.
Adversarial attacks in the physical world, particularly patch attacks, pose significant threats to the robustness and reliability of deep learning models. Developing reliable defenses against patch attacks is crucial for real-world applications, yet current research in this area is severely lacking. In this paper, we propose DIFFender, a novel defense method that leverages the pre-trained diffusion model to perform both localization and defense against potential adversarial patch attacks. DIFFender is designed as a pipeline consisting of two main stages: patch localization and restoration. In the localization stage, we exploit the intriguing properties of a diffusion model to effectively identify the locations of adversarial patches. In the restoration stage, we employ a text-guided diffusion model to eliminate adversarial regions in the image while preserving the integrity of the visual content. Additionally, we design a few-shot prompt-tuning algorithm to facilitate simple and efficient tuning, enabling the learned representations to easily transfer to downstream tasks, which optimize two stages jointly. We conduct extensive experiments on image classification and face recognition to demonstrate that DIFFender exhibits superior robustness under strong adaptive attacks and generalizes well across various scenarios, diverse classifiers, and multiple attack methods.
ML models are known to be vulnerable to adversarial query attacks. In these attacks, queries are iteratively perturbed towards a particular class without any knowledge of the target model besides its output. The prevalence of remotely-hosted ML classification models and Machine-Learning-as-a-Service platforms means that query attacks pose a real threat to the security of these systems. To deal with this, stateful defenses have been proposed to detect query attacks and prevent the generation of adversarial examples by monitoring and analyzing the sequence of queries received by the system. Several stateful defenses have been proposed in recent years. However, these defenses rely solely on similarity or out-of-distribution detection methods that may be effective in other domains. In the malware detection domain, the methods to generate adversarial examples are inherently different, and therefore we find that such detection mechanisms are significantly less effective. Hence, in this paper, we present MalProtect, which is a stateful defense against query attacks in the malware detection domain. MalProtect uses several threat indicators to detect attacks. Our results show that it reduces the evasion rate of adversarial query attacks by 80+\% in Android and Windows malware, across a range of attacker scenarios. In the first evaluation of its kind, we show that MalProtect outperforms prior stateful defenses, especially under the peak adversarial threat.
With the development of the Internet of Vehicles (IoV), vehicle wireless communication poses serious cybersecurity challenges. Faulty information, such as fake vehicle positions and speeds sent by surrounding vehicles, could cause vehicle collisions, traffic jams, and even casualties. Additionally, private vehicle data leakages, such as vehicle trajectory and user account information, may damage user property and security. Therefore, achieving a cyberattack-defense scheme in the IoV system with faulty data saturation is necessary. This paper proposes a Federated Learning-based Vehicle Trajectory Prediction Algorithm against Cyberattacks (FL-TP) to address the above problems. The FL-TP is intensively trained and tested using a publicly available Vehicular Reference Misbehavior (VeReMi) dataset with five types of cyberattacks: constant, constant offset, random, random offset, and eventual stop. The results show that the proposed FL-TP algorithm can improve cyberattack detection and trajectory prediction by up to 6.99% and 54.86%, respectively, under the maximum cyberattack permeability scenarios compared with benchmark methods.
Advanced persistent threats (APTs) have novel features such as multi-stage penetration, highly-tailored intention, and evasive tactics. APTs defense requires fusing multi-dimensional Cyber threat intelligence data to identify attack intentions and conducts efficient knowledge discovery strategies by data-driven machine learning to recognize entity relationships. However, data-driven machine learning lacks generalization ability on fresh or unknown samples, reducing the accuracy and practicality of the defense model. Besides, the private deployment of these APT defense models on heterogeneous environments and various network devices requires significant investment in context awareness (such as known attack entities, continuous network states, and current security strategies). In this paper, we propose a few-shot multi-domain knowledge rearming (FMKR) scheme for context-aware defense against APTs. By completing multiple small tasks that are generated from different network domains with meta-learning, the FMKR firstly trains a model with good discrimination and generalization ability for fresh and unknown APT attacks. In each FMKR task, both threat intelligence and local entities are fused into the support/query sets in meta-learning to identify possible attack stages. Secondly, to rearm current security strategies, an finetuning-based deployment mechanism is proposed to transfer learned knowledge into the student model, while minimizing the defense cost. Compared to multiple model replacement strategies, the FMKR provides a faster response to attack behaviors while consuming less scheduling cost. Based on the feedback from multiple real users of the Industrial Internet of Things (IIoT) over 2 months, we demonstrate that the proposed scheme can improve the defense satisfaction rate.
Federated learning (FL) naturally faces the problem of data heterogeneity in real-world scenarios, but this is often overlooked by studies on FL security and privacy. On the one hand, the effectiveness of backdoor attacks on FL may drop significantly under non-IID scenarios. On the other hand, malicious clients may steal private data through privacy inference attacks. Therefore, it is necessary to have a comprehensive perspective of data heterogeneity, backdoor, and privacy inference. In this paper, we propose a novel privacy inference-empowered stealthy backdoor attack (PI-SBA) scheme for FL under non-IID scenarios. Firstly, a diverse data reconstruction mechanism based on generative adversarial networks (GANs) is proposed to produce a supplementary dataset, which can improve the attacker's local data distribution and support more sophisticated strategies for backdoor attacks. Based on this, we design a source-specified backdoor learning (SSBL) strategy as a demonstration, allowing the adversary to arbitrarily specify which classes are susceptible to the backdoor trigger. Since the PI-SBA has an independent poisoned data synthesis process, it can be integrated into existing backdoor attacks to improve their effectiveness and stealthiness in non-IID scenarios. Extensive experiments based on MNIST, CIFAR10 and Youtube Aligned Face datasets demonstrate that the proposed PI-SBA scheme is effective in non-IID FL and stealthy against state-of-the-art defense methods.
As data are increasingly being stored in different silos and societies becoming more aware of data privacy issues, the traditional centralized training of artificial intelligence (AI) models is facing efficiency and privacy challenges. Recently, federated learning (FL) has emerged as an alternative solution and continue to thrive in this new reality. Existing FL protocol design has been shown to be vulnerable to adversaries within or outside of the system, compromising data privacy and system robustness. Besides training powerful global models, it is of paramount importance to design FL systems that have privacy guarantees and are resistant to different types of adversaries. In this paper, we conduct the first comprehensive survey on this topic. Through a concise introduction to the concept of FL, and a unique taxonomy covering: 1) threat models; 2) poisoning attacks and defenses against robustness; 3) inference attacks and defenses against privacy, we provide an accessible review of this important topic. We highlight the intuitions, key techniques as well as fundamental assumptions adopted by various attacks and defenses. Finally, we discuss promising future research directions towards robust and privacy-preserving federated learning.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191