As the technological advancement and capabilities of automated systems have increased drastically, the usage of unmanned aerial vehicles for performing human-dependent tasks without human indulgence has also spiked. Since unmanned aerial vehicles are heavily dependent on Information and Communication Technology, they are highly prone to cyber-attacks. With time more advanced and new attacks are being developed and employed. However, the current Intrusion detection system lacks detection and classification of new and unknown attacks. Therefore, for having an autonomous and reliable operation of unmanned aerial vehicles, more robust and automated cyber detection and protection schemes are needed. To address this, we have proposed an autonomous self-incremental learning architecture, capable of detecting known and unknown cyber-attacks on its own without any human interference. In our approach, we have combined signature-based detection along with anomaly detection in such a way that the signature-based detector autonomously updates its attack classes with the help of an anomaly detector. To achieve this, we have implemented an incremental learning approach, updating our model to incorporate new classes without forgetting the old ones. To validate the applicability and effectiveness of our proposed architecture, we have implemented it in a trial scenario and then compared it with the traditional offline learning approach. Moreover, our anomaly-based detector has achieved a 100% detection rate for attacks.
相關內容
Hardware (HW) security issues have been emerging at an alarming rate in recent years. Transient execution attacks, in particular, pose a genuine threat to the security of modern computing systems. Despite recent advances, understanding the intricate implications of microarchitectural design decisions on processor security remains a great challenge and has caused a number of update cycles in the past. number of update cycles in the past. This papers addresses the need for a new approach to HW sign-off verification which guarantees the security of processors at the Register Transfer Level (RTL). To this end, we introduce a formal definition of security with respect to transient execution attacks, formulated as a HW property. We present a formal proof methodology based on Unique Program Execution Checking (UPEC) which can be used to systematically detect all vulnerabilities to transient execution attacks in RTL designs. UPEC does not exploit any a priori knowledge on known attacks and can therefore detect also vulnerabilities based on new, so far unknown, types of channels. This is demonstrated by two new attack scenarios discovered in our experiments with UPEC. UPEC scales to a wide range of HW designs, including in-order processors (RocketChip), pipelines with out-of-order writeback (Ariane), and processors with deep out-of-order speculative execution (BOOM). To the best of our knowledge, UPEC is the first RTL verification technique that exhaustively covers transient execution side channels in processors of realistic complexity.
Machine learning algorithms are used to construct a mathematical model for a system based on training data. Such a model is capable of making highly accurate predictions without being explicitly programmed to do so. These techniques have a great many applications in all areas of the modern digital economy and artificial intelligence. More importantly, these methods are essential for a rapidly increasing number of safety-critical applications such as autonomous vehicles and intelligent defense systems. However, emerging adversarial learning attacks pose a serious security threat that greatly undermines further such systems. The latter are classified into four types, evasion (manipulating data to avoid detection), poisoning (injection malicious training samples to disrupt retraining), model stealing (extraction), and inference (leveraging over-generalization on training data). Understanding this type of attacks is a crucial first step for the development of effective countermeasures. The paper provides a detailed tutorial on the principles of adversarial machining learning, explains the different attack scenarios, and gives an in-depth insight into the state-of-art defense mechanisms against this rising threat .
Networked-Control Systems (NCSs), a type of cyber-physical systems, consist of tightly integrated computing, communication and control technologies. While being very flexible environments, they are vulnerable to computing and networking attacks. Recent NCSs hacking incidents had major impact. They call for more research on cyber-physical security. Fears about the use of quantum computing to break current cryptosystems make matters worse. While the quantum threat motivated the creation of new disciplines to handle the issue, such as post-quantum cryptography, other fields have overlooked the existence of quantum-enabled adversaries. This is the case of cyber-physical defense research, a distinct but complementary discipline to cyber-physical protection. Cyber-physical defense refers to the capability to detect and react in response to cyber-physical attacks. Concretely, it involves the integration of mechanisms to identify adverse events and prepare response plans, during and after incidents occur. In this paper, we make the assumption that the eventually available quantum computer will provide an advantage to adversaries against defenders, unless they also adopt this technology. We envision the necessity for a paradigm shift, where an increase of adversarial resources because of quantum supremacy does not translate into higher likelihood of disruptions. Consistently with current system design practices in other areas, such as the use of artificial intelligence for the reinforcement of attack detection tools, we outline a vision for next generation cyber-physical defense layers leveraging ideas from quantum computing and machine learning. Through an example, we show that defenders of NCSs can learn and improve their strategies to anticipate and recover from attacks.
The vulnerability against presentation attacks is a crucial problem undermining the wide-deployment of face recognition systems. Though presentation attack detection (PAD) systems try to address this problem, the lack of generalization and robustness continues to be a major concern. Several works have shown that using multi-channel PAD systems could alleviate this vulnerability and result in more robust systems. However, there is a wide selection of channels available for a PAD system such as RGB, Near Infrared, Shortwave Infrared, Depth, and Thermal sensors. Having a lot of sensors increases the cost of the system, and therefore an understanding of the performance of different sensors against a wide variety of attacks is necessary while selecting the modalities. In this work, we perform a comprehensive study to understand the effectiveness of various imaging modalities for PAD. The studies are performed on a multi-channel PAD dataset, collected with 14 different sensing modalities considering a wide range of 2D, 3D, and partial attacks. We used the multi-channel convolutional network-based architecture, which uses pixel-wise binary supervision. The model has been evaluated with different combinations of channels, and different image qualities on a variety of challenging known and unknown attack protocols. The results reveal interesting trends and can act as pointers for sensor selection for safety-critical presentation attack detection systems. The source codes and protocols to reproduce the results are made available publicly making it possible to extend this work to other architectures.
Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research opportunity in terms of cyber-security. This survey is conducted with a main intention of highlighting the most relevant information related to security vulnerabilities in the context of machine learning (ML) classifiers; more specifically, directed towards training procedures against data poisoning attacks, representing a type of attack that consists of tampering the data samples fed to the model during the training phase, leading to a degradation in the models accuracy during the inference phase. This work compiles the most relevant insights and findings found in the latest existing literatures addressing this type of attacks. Moreover, this paper also covers several defense techniques that promise feasible detection and mitigation mechanisms, capable of conferring a certain level of robustness to a target model against an attacker. A thorough assessment is performed on the reviewed works, comparing the effects of data poisoning on a wide range of ML models in real-world conditions, performing quantitative and qualitative analyses. This paper analyzes the main characteristics for each approach including performance success metrics, required hyperparameters, and deployment complexity. Moreover, this paper emphasizes the underlying assumptions and limitations considered by both attackers and defenders along with their intrinsic properties such as: availability, reliability, privacy, accountability, interpretability, etc. Finally, this paper concludes by making references of some of main existing research trends that provide pathways towards future research directions in the field of cyber-security.
Machine Learning (ML) techniques are increasingly adopted to tackle ever-evolving high-profile network attacks, including DDoS, botnet, and ransomware, due to their unique ability to extract complex patterns hidden in data streams. These approaches are however routinely validated with data collected in the same environment, and their performance degrades when deployed in different network topologies and/or applied on previously unseen traffic, as we uncover. This suggests malicious/benign behaviors are largely learned superficially and ML-based Network Intrusion Detection System (NIDS) need revisiting, to be effective in practice. In this paper we dive into the mechanics of large-scale network attacks, with a view to understanding how to use ML for Network Intrusion Detection (NID) in a principled way. We reveal that, although cyberattacks vary significantly in terms of payloads, vectors and targets, their early stages, which are critical to successful attack outcomes, share many similarities and exhibit important temporal correlations. Therefore, we treat NID as a time-sensitive task and propose NetSentry, perhaps the first of its kind NIDS that builds on Bidirectional Asymmetric LSTM (Bi-ALSTM), an original ensemble of sequential neural models, to detect network threats before they spread. We cross-evaluate NetSentry using two practical datasets, training on one and testing on the other, and demonstrate F1 score gains above 33% over the state-of-the-art, as well as up to 3 times higher rates of detecting attacks such as XSS and web bruteforce. Further, we put forward a novel data augmentation technique that boosts the generalization abilities of a broad range of supervised deep learning algorithms, leading to average F1 score gains above 35%.
The increasing interaction of industrial control systems (ICSs) with public networks and digital devices introduces new cyber threats to power systems and other critical infrastructure. Recent cyber-physical attacks such as Stuxnet and Irongate revealed unexpected ICS vulnerabilities and a need for improved security measures. Intrusion detection systems constitute a key security technology, which typically monitor network data for detecting malicious activities. However, a central characteristic of modern ICSs is the increasing interdependency of physical and cyber network processes. Thus, the integration of network and physical process data is seen as a promising approach to improve predictability in intrusion detection for ICSs by accounting for physical constraints and underlying process patterns. This work systematically assesses real-time cyber-physical intrusion detection and multiclass classification, based on a comparison to its purely network data-based counterpart and evaluation of misclassifications and detection delay. Multiple supervised machine learning models are applied on a recent cyber-physical dataset, describing various cyber attacks and physical faults on a generic ICS. A key finding is that integration of physical process data improves detection and classification of all attack types. In addition, it enables simultaneous processing of attacks and faults, paving the way for holistic cross-domain cause analysis.
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.
There is a rising interest in studying the robustness of deep neural network classifiers against adversaries, with both advanced attack and defence techniques being actively developed. However, most recent work focuses on discriminative classifiers, which only model the conditional distribution of the labels given the inputs. In this paper we propose the deep Bayes classifier, which improves classical naive Bayes with conditional deep generative models. We further develop detection methods for adversarial examples, which reject inputs that have negative log-likelihood under the generative model exceeding a threshold pre-specified using training data. Experimental results suggest that deep Bayes classifiers are more robust than deep discriminative classifiers, and the proposed detection methods achieve high detection rates against many recently proposed attacks.
In recent years, deep learning has shown performance breakthroughs in many applications, such as image detection, image segmentation, pose estimation, and speech recognition. However, this comes with a major concern: deep networks have been found to be vulnerable to adversarial examples. Adversarial examples are slightly modified inputs that are intentionally designed to cause a misclassification by the model. In the domains of images and speech, the modifications are so small that they are not seen or heard by humans, but nevertheless greatly affect the classification of the model. Deep learning models have been successfully applied to malware detection. In this domain, generating adversarial examples is not straightforward, as small modifications to the bytes of the file could lead to significant changes in its functionality and validity. We introduce a novel loss function for generating adversarial examples specifically tailored for discrete input sets, such as executable bytes. We modify malicious binaries so that they would be detected as benign, while preserving their original functionality, by injecting a small sequence of bytes (payload) in the binary file. We applied this approach to an end-to-end convolutional deep learning malware detection model and show a high rate of detection evasion. Moreover, we show that our generated payload is robust enough to be transferable within different locations of the same file and across different files, and that its entropy is low and similar to that of benign data sections.
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