In the recent years, we have witnessed quite notable cyber-attacks targeting industrial automation control systems. Upgrading their cyber security is a challenge, not only due to long equipment lifetimes and legacy protocols originally designed to run in air-gapped networks. Even where multiple data sources are available and collection established, data interpretation usable across the different data sources remains a challenge. A modern hydro power plant contains the data sources that range from the classical distributed control systems to newer IoT- based data sources, embedded directly within the plant equipment and deeply integrated in the process. Even abundant collected data does not solve the security problems by itself. The interpretation of data semantics is limited as the data is effectively siloed. In this paper, the relevance of semantic integration of diverse data sources is presented in the context of a hydro power plant. The proposed semantic integration would increase the data interoperability, unlocking the data siloes and thus allowing ingestion of complementary data sources. The principal target of the data interoperability is to support the data-enhanced cyber security in an operational hydro power plant context. Furthermore, the opening of the data siloes would enable additional usage of the existing data sources in a structured semantically enriched form.

Unmanned Aerial Vehicles (UAVs) are drawing enormous attention in both commercial and military applications to facilitate dynamic wireless communications and deliver seamless connectivity due to their flexible deployment, inherent line-of-sight (LOS) air-to-ground (A2G) channels, and high mobility. These advantages, however, render UAV-enabled wireless communication systems susceptible to eavesdropping attempts. Hence, there is a strong need to protect the wireless channel through which most of the UAV-enabled applications share data with each other. There exist various error correction techniques such as Low Density Parity Check (LDPC), polar codes that provide safe and reliable data transmission by exploiting the physical layer but require high transmission power. Also, the security gap achieved by these error-correction techniques must be reduced to improve the security level. In this paper, we present deep learning (DL) enabled punctured LDPC codes to provide secure and reliable transmission of data for UAVs through the Additive White Gaussian Noise (AWGN) channel irrespective of the computational power and channel state information (CSI) of the Eavesdropper. Numerical result analysis shows that the proposed scheme reduces the Bit Error Rate (BER) at Bob effectively as compared to Eve and the Signal to Noise Ratio (SNR) per bit value of 3.5 dB is achieved at the maximum threshold value of BER. Also, the security gap is reduced by 47.22 % as compared to conventional LDPC codes.

Shipboard marine radar systems are essential for safe navigation, helping seafarers perceive their surroundings as they provide bearing and range estimations, object detection, and tracking. Since onboard systems have become increasingly digitized, interconnecting distributed electronics, radars have been integrated into modern bridge systems. But digitization increases the risk of cyberattacks, especially as vessels cannot be considered air-gapped. Consequently, in-depth security is crucial. However, particularly radar systems are not sufficiently protected against harmful network-level adversaries. Therefore, we ask: Can seafarers believe their eyes? In this paper, we identify possible attacks on radar communication and discuss how these threaten safe vessel operation in an attack taxonomy. Furthermore, we develop a holistic simulation environment with radar, complementary nautical sensors, and prototypically implemented cyberattacks from our taxonomy. Finally, leveraging this environment, we create a comprehensive dataset (RadarPWN) with radar network attacks that provides a foundation for future security research to secure marine radar communication.

As the effects of climate change are becoming more and more evident, the importance of improved situation awareness is also gaining more attention, both in the context of preventive environmental monitoring and in the context of acute crisis response. One important aspect of situation awareness is the correct and thorough monitoring of air pollutants. The monitoring is threatened by sensor faults, power or network failures, or other hazards leading to missing or incorrect data transmission. For this reason, in this work we propose two complementary approaches for predicting missing sensor data and a combined technique for detecting outliers. The proposed solution can enhance the performance of low-cost sensor systems, closing the gap of missing measurements due to network unavailability, detecting drift and outliers thus paving the way to its use as an alert system for reportable events. The techniques have been deployed and tested also in a low power microcontroller environment, verifying the suitability of such a computing power to perform the inference locally, leading the way to an edge implementation of a virtual sensor digital twin.

We introduce AdaMix, an adaptive differentially private algorithm for training deep neural network classifiers using both private and public image data. While pre-training language models on large public datasets has enabled strong differential privacy (DP) guarantees with minor loss of accuracy, a similar practice yields punishing trade-offs in vision tasks. A few-shot or even zero-shot learning baseline that ignores private data can outperform fine-tuning on a large private dataset. AdaMix incorporates few-shot training, or cross-modal zero-shot learning, on public data prior to private fine-tuning, to improve the trade-off. AdaMix reduces the error increase from the non-private upper bound from the 167–311% of the baseline, on average across 6 datasets, to 68-92% depending on the desired privacy level selected by the user. AdaMix tackles the trade-off arising in visual classification, whereby the most privacy sensitive data, corresponding to isolated points in representation space, are also critical for high classification accuracy. In addition, AdaMix comes with strong theoretical privacy guarantees and convergence analysis.

This paper proposes a novel approach for privacy preserving face recognition aimed to formally define a trade-off optimization criterion between data privacy and algorithm accuracy. In our methodology, real world face images are anonymized with Gaussian blurring for privacy preservation. The anonymized images are processed for face detection, face alignment, face representation, and face verification. The proposed methodology has been validated with a set of experiments on a well known dataset and three face recognition classifiers. The results demonstrate the effectiveness of our approach to correctly verify face images with different levels of privacy and results accuracy, and to maximize privacy with the least negative impact on face detection and face verification accuracy.

Modern consumer electronic devices often provide intelligence services with deep neural networks. We have started migrating the computing locations of intelligence services from cloud servers (traditional AI systems) to the corresponding devices (on-device AI systems). On-device AI systems generally have the advantages of preserving privacy, removing network latency, and saving cloud costs. With the emergence of on-device AI systems having relatively low computing power, the inconsistent and varying hardware resources and capabilities pose difficulties. Authors' affiliation has started applying a stream pipeline framework, NNStreamer, for on-device AI systems, saving developmental costs and hardware resources and improving performance. We want to expand the types of devices and applications with on-device AI services products of both the affiliation and second/third parties. We also want to make each AI service atomic, re-deployable, and shared among connected devices of arbitrary vendors; we now have yet another requirement introduced as it always has been. The new requirement of “among-device AI” includes connectivity between AI pipelines so that they may share computing resources and hardware capabilities across a wide range of devices regardless of vendors and manufacturers. We propose extensions of the stream pipeline framework, NNStreamer, for on-device AI so that NNStreamer may provide among-device AI capability. This work is a Linux Foundation (LF AI & Data) open source project accepting contributions from the general public.

Throughout history, technological evolution has generated less desired side effects with impact on society. In the field of IT&C, there are ongoing discussions about the role of robots within economy, but also about their impact on the labour market. In the case of digital media systems, we talk about misinformation, manipulation, fake news, etc. Issues related to the protection of the citizen's life in the face of technology began more than 25 years ago; In addition to the many messages such as “the citizen is at the center of concern” or, “privacy must be respected”, transmitted through various channels of different entities or companies in the field of ICT, the EU has promoted a number of legislative and normative documents to protect citizens' rights and freedoms.

With 3.78 billion social media users worldwide in 2021 (48% of the human population), almost 3 billion images are shared daily. At the same time, a consistent evolution of smartphone cameras has led to a photography explosion with 85% of all new pictures being captured using smartphones. However, lately, there has been an increased discussion of privacy concerns when a person being photographed is unaware of the picture being taken or has reservations about the same being shared. These privacy violations are amplified for people with disabilities, who may find it challenging to raise dissent even if they are aware. Such unauthorized image captures may also be misused to gain sympathy by third-party organizations, leading to a privacy breach. Privacy for people with disabilities has so far received comparatively less attention from the AI community. This motivates us to work towards a solution to generate privacy-conscious cues for raising awareness in smartphone users of any sensitivity in their viewfinder content. To this end, we introduce PrivPAS (A real time Privacy-Preserving AI System) a novel framework to identify sensitive content. Additionally, we curate and annotate a dataset to identify and localize accessibility markers and classify whether an image is sensitive to a featured subject with a disability. We demonstrate that the proposed lightweight architecture, with a memory footprint of a mere 8.49MB, achieves a high mAP of 89.52% on resource-constrained devices. Furthermore, our pipeline, trained on face anonymized data. achieves an F1-score of 73.1%.

Blockchain and artificial intelligence are two technologies that, when combined, have the ability to help each other realize their full potential. Blockchains can guarantee the accessibility and consistent admittance to integrity safeguarded big data indexes from numerous areas, allowing AI systems to learn more effectively and thoroughly. Similarly, artificial intelligence (AI) can be used to offer new consensus processes, and hence new methods of engaging with Blockchains. When it comes to sensitive data, such as corporate, healthcare, and financial data, various security and privacy problems arise that must be properly evaluated. Interaction with Blockchains is vulnerable to data credibility checks, transactional data leakages, data protection rules compliance, on-chain data privacy, and malicious smart contracts. To solve these issues, new security and privacy-preserving technologies are being developed. AI-based blockchain data processing, either based on AI or used to defend AI-based blockchain data processing, is emerging to simplify the integration of these two cutting-edge technologies.

This paper focuses on the system on wireless sensor networks. The system is linear and the time of the system is discrete as well as variable, which named discrete-time linear time-varying systems (DLTVS). DLTVS are vulnerable to network attacks when exchanging information between sensors in the network, as well as putting their security at risk. A DLTVS with privacy-preserving is designed for this purpose. A set-membership estimator is designed by adding privacy noise obeying the Laplace distribution to state at the initial moment. Simultaneously, the differential privacy of the system is analyzed. On this basis, the real state of the system and the existence form of the estimator for the desired distribution are analyzed. Finally, simulation examples are given, which prove that the model after adding differential privacy can obtain accurate estimates and ensure the security of the system state.

Research done in Facial Privacy so far has entrenched the scope of gleaning race, age, and gender from a human’s facial image that are classifiable and compliant biometric attributes. Noticeable distortions, morphing, and face-swapping are some of the techniques that have been researched to restore consumers’ privacy. By fooling face recognition models, these techniques cater superficially to the needs of user privacy, however, the presence of visible manipulations negatively affects the aesthetic of the image. The objective of this work is to highlight common adversarial techniques that can be used to introduce granular pixel distortions using white-box and black-box perturbation algorithms that ensure the privacy of users’ sensitive or personal data in face images, fooling AI facial recognition models while maintaining the aesthetics of and visual integrity of the image.

The integration of the Internet-of-Vehicles (IoV) and fog computing benefits from cooperative computing and analysis of environmental data while avoiding network congestion and latency. However, when private data is shared across fog nodes or the cloud, there exist privacy issues that limit the effectiveness of IoV systems, putting drivers' safety at risk. To address this problem, we propose a framework called PPIoV, which is based on Federated Learning (FL) and Blockchain technologies to preserve the privacy of vehicles in IoV.Typical machine learning methods are not well suited for distributed and highly dynamic systems like IoV since they train on data with local features. Therefore, we use FL to train the global model while preserving privacy. Also, our approach is built on a scheme that evaluates the reliability of vehicles participating in the FL training process. Moreover, PPIoV is built on blockchain to establish trust across multiple communication nodes. For example, when the local learned model updates from the vehicles and fog nodes are communicated with the cloud to update the global learned model, all transactions take place on the blockchain. The outcome of our experimental study shows that the proposed method improves the global model's accuracy as a result of allowing reputed vehicles to update the global model.

With the development of artificial intelligence, the need for data sharing is becoming more and more urgent. However, the existing data sharing methods can no longer fully meet the data sharing needs. Privacy breaches, lack of motivation and mutual distrust have become obstacles to data sharing. We design a privacy-preserving, decentralized data sharing method based on blockchain smart contracts, named PPDS. To protect data privacy, we transform the data sharing problem into a model sharing problem. This means that the data owner does not need to directly share the raw data, but the AI model trained with such data. The data requester and the data owner interact on the blockchain through a smart contract. The data owner trains the model with local data according to the requester's requirements. To fairly assess model quality, we set up several model evaluators to assess the validity of the model through voting. After the model is verified, the data owner who trained the model will receive reward in return through a smart contract. The sharing of the model avoids direct exposure of the raw data, and the reasonable incentive provides a motivation for the data owner to share the data. We describe the design and workflow of our PPDS, and analyze the security using formal verification technology, that is, we use Coloured Petri Nets (CPN) to build a formal model for our approach, proving its security through simulation execution and model checking. Finally, we demonstrate effectiveness of PPDS by developing a prototype with its corresponding case application.

Nowadays, IoT networks and devices exist in our everyday life, capturing and carrying unlimited data. However, increasing penetration of connected systems and devices implies rising threats for cybersecurity with IoT systems suffering from network attacks. Artificial Intelligence (AI) and Machine Learning take advantage of huge volumes of IoT network logs to enhance their cybersecurity in IoT. However, these data are often desired to remain private. Federated Learning (FL) provides a potential solution which enables collaborative training of attack detection model among a set of federated nodes, while preserving privacy as data remain local and are never disclosed or processed on central servers. While FL is resilient and resolves, up to a point, data governance and ownership issues, it does not guarantee security and privacy by design. Adversaries could interfere with the communication process, expose network vulnerabilities, and manipulate the training process, thus affecting the performance of the trained model. In this paper, we present a federated learning model which can successfully detect network attacks in IoT systems. Moreover, we evaluate its performance under various settings of differential privacy as a privacy preserving technique and configurations of the participating nodes. We prove that the proposed model protects the privacy without actually compromising performance. Our model realizes a limited performance impact of only ∼ 7% less testing accuracy compared to the baseline while simultaneously guaranteeing security and applicability.

Graph-based Semi-Supervised Learning (GSSL) is a practical solution to learn from a limited amount of labelled data together with a vast amount of unlabelled data. However, due to their reliance on the known labels to infer the unknown labels, these algorithms are sensitive to data quality. It is therefore essential to study the potential threats related to the labelled data, more specifically, label poisoning. In this paper, we propose a novel data poisoning method which efficiently approximates the result of label inference to identify the inputs which, if poisoned, would produce the highest number of incorrectly inferred labels. We extensively evaluate our approach on three classification problems under 24 different experimental settings each. Compared to the state of the art, our influence-driven attack produces an average increase of error rate 50% higher, while being faster by multiple orders of magnitude. Moreover, our method can inform engineers of inputs that deserve investigation (relabelling them) before training the learning model. We show that relabelling one-third of the poisoned inputs (selected based on their influence) reduces the poisoning effect by 50%. ACM Reference Format: Adriano Franci, Maxime Cordy, Martin Gubri, Mike Papadakis, and Yves Le Traon. 2022. Influence-Driven Data Poisoning in Graph-Based Semi-Supervised Classifiers. In 1st Conference on AI Engineering - Software Engineering for AI (CAIN’22), May 16–24, 2022, Pittsburgh, PA, USA. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3522664.3528606

Recent trends in the convergence of edge computing and artificial intelligence (AI) have led to a new paradigm of “edge intelligence”, which are more vulnerable to attack such as data and model poisoning and evasion of attacks. This paper proposes a white-box poisoning attack against online regression model for edge intelligence environment, which aim to prepare the protection methods in the future. Firstly, the new method selects data points from original stream with maximum loss by two selection strategies; Secondly, it pollutes these points with gradient ascent strategy. At last, it injects polluted points into original stream being sent to target model to complete the attack process. We extensively evaluate our proposed attack on open dataset, the results of which demonstrate the effectiveness of the novel attack method and the real implications of poisoning attack in a case study electric energy prediction application.

With the widespread deployment of data-driven services, the demand for data volumes continues to grow. At present, many applications lack reliable human supervision in the process of data collection, which makes the collected data contain low-quality data or even malicious data. This low-quality or malicious data make AI systems potentially face much security challenges. One of the main security threats in the training phase of machine learning is data poisoning attacks, which compromise model integrity by contaminating training data to make the resulting model skewed or unusable. This paper reviews the relevant researches on data poisoning attacks in various task environments: first, the classification of attacks is summarized, then the defense methods of data poisoning attacks are sorted out, and finally, the possible research directions in the prospect.

In recent years, the security of AI systems has drawn increasing research attention, especially in the medical imaging realm. To develop a secure medical image analysis (MIA) system, it is a must to study possible backdoor attacks (BAs), which can embed hidden malicious behaviors into the system. However, designing a unified BA method that can be applied to various MIA systems is challenging due to the diversity of imaging modalities (e.g., X-Ray, CT, and MRI) and analysis tasks (e.g., classification, detection, and segmentation). Most existing BA methods are designed to attack natural image classification models, which apply spatial triggers to training images and inevitably corrupt the semantics of poisoned pixels, leading to the failures of attacking dense prediction models. To address this issue, we propose a novel Frequency-Injection based Backdoor Attack method (FIBA) that is capable of delivering attacks in various MIA tasks. Specifically, FIBA leverages a trigger function in the frequency domain that can inject the low-frequency information of a trigger image into the poisoned image by linearly combining the spectral amplitude of both images. Since it preserves the semantics of the poisoned image pixels, FIBA can perform attacks on both classification and dense prediction models. Experiments on three benchmarks in MIA (i.e., ISIC-2019 [4] for skin lesion classification, KiTS-19 [17] for kidney tumor segmentation, and EAD-2019 [1] for endoscopic artifact detection), validate the effectiveness of FIBA and its superiority over stateof-the-art methods in attacking MIA models and bypassing backdoor defense. Source code will be available at code.

Federated learning (FL) has emerged as a promising paradigm for distributed training of machine learning models. In FL, several participants train a global model collaboratively by only sharing model parameter updates while keeping their training data local. However, FL was recently shown to be vulnerable to data poisoning attacks, in which malicious participants send parameter updates derived from poisoned training data. In this paper, we focus on defending against targeted data poisoning attacks, where the attacker’s goal is to make the model misbehave for a small subset of classes while the rest of the model is relatively unaffected. To defend against such attacks, we first propose a method called MAPPS for separating malicious updates from benign ones. Using MAPPS, we propose three methods for attack detection: MAPPS + X-Means, MAPPS + VAT, and their Ensemble. Then, we propose an attack mitigation approach in which a "clean" model (i.e., a model that is not negatively impacted by an attack) can be trained despite the existence of a poisoning attempt. We empirically evaluate all of our methods using popular image classification datasets. Results show that we can achieve \textgreater 95% true positive rates while incurring only \textless 2% false positive rate. Furthermore, the clean models that are trained using our proposed methods have accuracy comparable to models trained in an attack-free scenario.

Machine Learning (ML) and Artificial Intelligence (AI) techniques are widely adopted in the telecommunication industry, especially to automate beyond 5G networks. Federated Learning (FL) recently emerged as a distributed ML approach that enables localized model training to keep data decentralized to ensure data privacy. In this paper, we identify the applicability of FL for securing future networks and its limitations due to the vulnerability to poisoning attacks. First, we investigate the shortcomings of state-of-the-art security algorithms for FL and perform an attack to circumvent FoolsGold algorithm, which is known as one of the most promising defense techniques currently available. The attack is launched with the addition of intelligent noise at the poisonous model updates. Then we propose a more sophisticated defense strategy, a threshold-based clustering mechanism to complement FoolsGold. Moreover, we provide a comprehensive analysis of the impact of the attack scenario and the performance of the defense mechanism.

Existing defense strategies against adversarial attacks (AAs) on AI/ML are primarily focused on examining the input data streams using a wide variety of filtering techniques. For instance, input filters are used to remove noisy, misleading, and out-of-class inputs along with a variety of attacks on learning systems. However, a single filter may not be able to detect all types of AAs. To address this issue, in the current work, we propose a robust, transferable, distribution-independent, and cross-domain supported framework for selecting Adaptive Filter Ensembles (AFEs) to minimize the impact of data poisoning on learning systems. The optimal filter ensembles are determined through a Multi-Objective Bi-Level Programming Problem (MOBLPP) that provides a subset of diverse filter sequences, each exhibiting fair detection accuracy. The proposed framework of AFE is trained to model the pristine data distribution to identify the corrupted inputs and converges to the optimal AFE without vanishing gradients and mode collapses irrespective of input data distributions. We presented preliminary experiments to show the proposed defense outperforms the existing defenses in terms of robustness and accuracy.

Trojan attacks threaten deep neural networks (DNNs) by poisoning them to behave normally on most samples, yet to produce manipulated results for inputs attached with a particular trigger. Several works attempt to detect whether a given DNN has been injected with a specific trigger during the training. In a parallel line of research, the lottery ticket hypothesis reveals the existence of sparse sub-networks which are capable of reaching competitive performance as the dense network after independent training. Connecting these two dots, we investigate the problem of Trojan DNN detection from the brand new lens of sparsity, even when no clean training data is available. Our crucial observation is that the Trojan features are significantly more stable to network pruning than benign features. Leveraging that, we propose a novel Trojan network detection regime: first locating a “winning Trojan lottery ticket” which preserves nearly full Trojan information yet only chance-level performance on clean inputs; then recovering the trigger embedded in this already isolated sub-network. Extensive experiments on various datasets, i.e., CIFAR-10, CIFAR-100, and ImageNet, with different network architectures, i.e., VGG-16, ResNet-18, ResNet-20s, and DenseNet-100 demonstrate the effectiveness of our proposal. Codes are available at https://github.com/VITA-Group/Backdoor-LTH.

Realize the same-city and remote disaster recovery of the infectious disease network direct reporting system of the China Medical Archives Information Center. Method: A three-tier B/S/DBMS architecture is used in the disaster recovery center to deploy an infectious disease network direct reporting system, and realize data-level disaster recovery through remote replication technology; realize application-level disaster recovery of key business systems through asynchronous data technology; through asynchronous the mode carries on the network direct report system disaster tolerance data transmission of medical files. The establishment of disaster recovery centers in different cities in the same city ensures the direct reporting system and data security of infectious diseases, and ensures the effective progress of continuity work. The results show that the efficiency of remote disaster recovery and backup based on big data has increased by 9.2%

The data centers of cloud computing-based aerospace ground systems and the businesses running on them are extremely vulnerable to man-made disasters, emergencies, and other disasters, which means security is seriously threatened. Thus, cloud centers need to provide effective disaster recovery services for software and data. However, the disaster recovery methods for current cloud centers of aerospace ground systems have long been in arrears, and the disaster tolerance and anti-destruction capability are weak. Aiming at the above problems, in this paper we design a disaster recovery service for aerospace ground systems based on cloud computing. On account of the software warehouse, this service adopts the main standby mode to achieve the backup, local disaster recovery, and remote disaster recovery of software and data. As a result, this service can timely response to the disasters, ensure the continuous running of businesses, and improve the disaster tolerance and anti-destruction capability of aerospace ground systems. Extensive simulation experiments validate the effectiveness of the disaster recovery service proposed in this paper.