Biblio

The complexity and scale of modern software programs often lead to overlooked programming errors and security vulnerabilities. Developers often rely on automatic tools, like static analysis tools, to look for bugs and vulnerabilities. Static analysis tools are widely used because they can understand nontrivial program behaviors, scale to millions of lines of code, and detect subtle bugs. However, they are known to generate an excess of false alarms which hinder their utilization as it is counterproductive for developers to go through a long list of reported issues, only to find a few true positives. One of the ways proposed to suppress false positives is to use machine learning to identify them. However, training machine learning models requires good quality labeled datasets. For this purpose, we developed D2A [3], a differential analysis based approach that uses the commit history of a code repository to create a labeled dataset of Infer [2] static analysis output.

The increasing demand for the interconnected IoT based smart grid is facing threats from cyber-attacks due to inherent vulnerability in the smart grid network. There is a pressing need to evaluate and model these vulnerabilities in the network to avoid cascading failures in power systems. In this paper, we propose and evaluate a vulnerability assessment framework based on attack probability for the protection and security of a smart grid. Several factors were taken into consideration such as the probability of attack, propagation of attack from a parent node to child nodes, effectiveness of basic metering system, Kalman estimation and Advanced Metering Infrastructure (AMI). The IEEE-300 bus smart grid was simulated using MATPOWER to study the effectiveness of the proposed framework by injecting false data injection attacks (FDIA); and studying their propagation. Our results show that the use of severity assessment standards such as Common Vulnerability Scoring System (CVSS), AMI measurements and Kalman estimates were very effective for evaluating the vulnerability assessment of smart grid in the presence of FDIA attack scenarios.

Smart grid (SG) is considered the next generation of the traditional power grid. It is mainly divided into three main infrastructures: power system, information and communication infrastructures. Cybersecurity is imperative for information infrastructure and the secure, reliable, and efficient operation of the smart grid. Cybersecurity or a lack of proper implementation thereof poses a considerable challenge to the deployment of SG. Therefore, in this paper, A comprehensive survey of cyber security is presented in the smart grid context. Cybersecurity-related information infrastructure is clarified. The impact of adopting cybersecurity on control and management systems has been discussed. Also, the paper highlights the cybersecurity issues and challenges associated with the control decisions in the smart grid.

An accurate state estimation (SE) considering increased uncertainty by the high penetration of renewable energy systems (RESs) is more and more important to enhance situational awareness, and the optimal and resilient operation of the renewable-rich power grids. However, it is anticipated that adversaries who plan to manipulate the target power grid will generate attacks that inject inaccurate data to the SE using the vulnerabilities of the devices and networks. Among potential attack types, false data injection attack (FDIA) is gaining popularity since this can bypass bad data detection (BDD) methods implemented in the SE systems. Although numerous FDIA detection methods have been recently proposed, the uncertainty of system configuration that arises by the continuously increasing penetration of RESs has been been given less consideration in the FDIA algorithms. To address this issue, this paper proposes a new FDIA detection scheme that is applicable to renewable energy-rich power grids. A deep learning framework is developed in particular by synergistically constructing a Bidirectional Long Short-Term Memory (Bi-LSTM) with modern smart grid characteristics. The developed framework is evaluated on the IEEE 14-bus system integrating several RESs by using several attack scenarios. A comparison of the numerical results shows that the proposed FDIA detection mechanism outperforms the existing deep learning-based approaches in a renewable energy-rich grid environment.

The integration of distributed energy resources (DERs) and expansion of complex network in the distribution grid requires an advanced two-level state estimator to monitor the grid health at micro-level. The distribution state estimator will improve the situational awareness and resiliency of distributed power system. This paper implements a synchrophasors-based master state awareness (MSA) estimator to enhance the cybersecurity in distribution grid by providing a real-time estimation of system operating states to control center operators. In this paper, the implemented MSA estimator utilizes only phasor measurements, bus magnitudes and angles, from phasor measurement units (PMUs), deployed in local substations, to estimate the system states and also detects data integrity attacks, such as load tripping attack that disconnects the load. To validate the proof of concept, we implement this methodology in cyber-physical testbed environment at the Idaho National Laboratory (INL) Electric Grid Security Testbed. Further, to address the "valley of death" and support technology commercialization, field demonstration is also performed at the Critical Infrastructure Test Range Complex (CITRC) at the INL. Our experimental results reveal a promising performance in detecting load tripping attack and providing an accurate situational awareness through an alert visualization dashboard in real-time.

Increasing connectivity and automation in vehicles leads to a greater potential attack surface. Such vulnerabilities within vehicles can also be used for auto-theft, increasing the potential for attackers to disable anti-theft mechanisms implemented by vehicle manufacturers. We utilize patterns derived from Controller Area Network (CAN) bus traffic to verify driver “behavior”, as a basis to prevent vehicle theft. Our proposed model uses semi-supervised learning that continuously profiles a driver, using features extracted from CAN bus traffic. We have selected 15 key features and obtained an accuracy of 99% using a dataset comprising a total of 51 features across 10 different drivers. We use a number of data analysis algorithms, such as J48, Random Forest, JRip and clustering, using 94K records. Our results show that J48 is the best performing algorithm in terms of training and testing (1.95 seconds and 0.44 seconds recorded, respectively). We also analyze the effect of using a sliding window on algorithm performance, altering the size of the window to identify the impact on prediction accuracy.

Peer-to-peer (P2P) energy trading is one of the promising approaches for implementing decentralized electricity market paradigms. In the P2P trading, each actor negotiates directly with a set of trading partners. Since the physical network or grid is used for energy transfer, power losses are inevitable, and grid-related costs always occur during the P2P trading. A proper market clearing mechanism is required for the P2P energy trading between different producers and consumers. This paper proposes a decentralized market clearing mechanism for the P2P energy trading considering the privacy of the agents, power losses as well as the utilization fees for using the third party owned network. Grid-related costs in the P2P energy trading are considered by calculating the network utilization fees using an electrical distance approach. The simulation results are presented to verify the effectiveness of the proposed decentralized approach for market clearing in P2P energy trading.

Smart metering is a mechanism through which fine-grained electricity usage data of consumers is collected periodically in a smart grid. However, a growing concern in this regard is that the leakage of consumers' consumption data may reveal their daily life patterns as the state-of-the-art metering strategies lack adequate security and privacy measures. Many proposed solutions have demonstrated how the aggregated metering information can be transformed to obscure individual consumption patterns without affecting the intended semantics of smart grid operations. In this paper, we expose a complete break of such an existing privacy preserving metering scheme [10] by determining individual consumption patterns efficiently, thus compromising its privacy guarantees. The underlying methodol-ogy of this scheme allows us to - i) retrieve the lower bounds of the privacy parameters and ii) establish a relationship between the privacy preserved output readings and the initial input readings. Subsequently, we present a rigorous experimental validation of our proposed attacking methodology using real-life dataset to highlight its efficacy. In summary, the present paper queries: Is the Whole lesser than its Parts? for such privacy aware metering algorithms which attempt to reduce the information leakage of aggregated consumption patterns of the individuals.

Demand response has emerged as one of the most promising methods for the deployment of sustainable energy systems. Attempts to democratize demand response and establish programs for residential consumers have run into scalability issues and risks of leaking sensitive consumer data. In this work, we propose a privacy-friendly, incentive-based demand response market, where consumers offer their flexibility to utilities in exchange for a financial compensation. Consumers submit encrypted offer which are aggregated using Computation Over Encrypted Data to ensure consumer privacy and the scalability of the approach. The optimal allocation of flexibility is then determined via double-auctions, along with the optimal consumption schedule for the users with respect to the day-ahead electricity prices, thus also shielding participants from high electricity prices. A case study is presented to show the effectiveness of the proposed approach.

Satisfying the growing demand for electricity is a huge challenge for electricity providers without a robust and good infrastructure. For effective electricity management, the infrastructure has to be strengthened from the generation stage to the transmission and distribution stages. In the current electrical infrastructure, the evolution of smart grids provides a significant solution to the problems that exist in the conventional system. Enhanced management visibility and better monitoring and control are achieved by the integration of wireless sensor network technology in communication systems. However, to implement these solutions in the existing grids, the infrastructural constraints impose a major challenge. Along with the choice of technology, it is also crucial to avoid exorbitant implementation costs. This paper presents a self-stabilizing hierarchical algorithm for the existing electrical network. Neighborhood Area Networks (NAN) and Home Area Networks (HAN) layers are used in the proposed architecture. The Home Node (HN), Simple Node (SN) and Cluster Head (CH) are the three types of nodes used in the model. Fraudulent users in the system are identified efficiently using the proposed model based on the observations made through simulation on OMNeT++ simulator.

Current sensors are widely used in power grid for power metering, automation and power equipment monitoring. Since the tradeoff between the sensitivity and the measurement range needs to be made to design a current sensor, it is difficult to deploy one sensor to measure both the small-magnitude and the large-magnitude current. In this research, we design a surface-mount current sensor by using the tunneling magneto-resistance (TMR) devices and show that the tradeoff between the sensitivity and the detection range can be broken. Two TMR devices of different sensitivity degrees were integrated into one current sensor module, and a signal processing algorithm was implemented to fusion the outputs of the two TMR devices. Then, a platform was setup to test the performance of the surface-mount current sensor. The results showed that the designed current sensor could measure the current from 2 mA to 100 A with an approximate 93 dB dynamic range. Besides, the nonintrusive feature of the surface-mount current sensor could make it convenient to be deployed on-site.

For some countries around the world, meeting demand is a serious concern. Power supply market is increasingly increasing, posing a big challenge for various countries throughout the world. The increasing expansion in the market for power needs upgrading system dependability to increase the smart grid's resilience. This smart electric grid has a sensor that analyses grid power availability and sends regular updates to the organisation. The internet is currently being utilized to monitor processes and place orders for running variables from faraway places. A large number of scanners have been used to activate electrical equipment for domestic robotics for a long period in the last several days. Conversely, if it is not correctly implemented, it will have a negative impact on cost-effectiveness as well as productivity. For something like a long time, home automation has relied on a large number of sensor nodes to control electrical equipment. Since there are so many detectors, this isn't cost-effective. In this article, develop and accept a wireless communication component and a management system suitable for managing independent efficient network units from voltage rises and voltage control technologies in simultaneous analyzing system reliability in this study. This research paper has considered secondary method to collect relevant and in-depth data related to the wireless sensor network and its usage in smart grid monitoring.

Traditional power consumption management systems are not showing enough reliability and thus, smart grid technology has been introduced to reduce the excess power wastages. In the context of smart grid systems, network communication is another term that is used for developing the network between the users and the load profiles. Cloud computing and clustering are also executed for efficient power management. Based on the facts, this research is going to identify wireless network communication systems to monitor and control smart grid power consumption. Primary survey-based research has been carried out with 62 individuals who worked in the smart grid system, tracked, monitored and controlled the power consumptions using WSN technology. The survey was conducted online where the respondents provided their opinions via a google survey form. The responses were collected and analyzed on Microsoft Excel. Results show that hybrid commuting of cloud and edge computing technology is more advantageous than individual computing. Respondents agreed that deep learning techniques will be more beneficial to analyze load profiles than machine learning techniques. Lastly, the study has explained the advantages and challenges of using smart grid network communication systems. Apart from the findings from primary research, secondary journal articles were also observed to emphasize the research findings.

Firewalls are security devices that perform network traffic filtering. They are ubiquitous in the industry and are a common method used to enforce organizational security policy. Security policy is specified on a high level of abstraction, with statements such as "web browsing is allowed only on workstations inside the office network", and needs to be translated into low-level firewall rules to be enforceable. There has been a lot of work regarding optimization, analysis and platform independence of firewall rules, but an area that has seen much less success is automatic translation of high-level security policies into firewall rules. In addition to improving rules’ readability, such translation would make it easier to detect errors.This paper surveys of over twenty papers that aim to generate firewall rules according to a security policy specified on a higher level of abstraction. It also presents an overview of similar features in modern firewall systems. Most approaches define specialized domain languages that get compiled into firewall rule sets, with some of them relying on formal specification, ontology, or graphical models. The approaches’ have improved over time, but there are still many drawbacks that need to be solved before wider application.

In response to the vulnerabilities in traditional perimeter-based network security, the zero trust framework is a promising approach to secure modern network systems and address the challenges. The core of zero trust security is agent-centric trust evaluation and trust-based security decisions. The challenges, however, arise from the limited observations of the agent's footprint and asymmetric information in the decision-making. An effective trust policy needs to tradeoff between the security and usability of the network. The explainability of the policy facilitates the human understanding of the policy, the trust of the result, as well as the adoption of the technology. To this end, we formulate a zero-trust defense model using Partially Observable Markov Decision Processes (POMDP), which captures the uncertainties in the observations of the defender. The framework leads to an explainable trust-threshold policy that determines the defense policy based on the trust scores. This policy is shown to achieve optimal performance under mild conditions. The trust threshold enables an efficient algorithm to compute the defense policy while providing online learning capabilities. We use an enterprise network as a case study to corroborate the results. We discuss key factors on the trust threshold and illustrate how the trust threshold policy can adapt to different environments.

At present, the black-start mode of the large power grid is mostly limited to relying on the black-start power supply inside the system, or only to the recovery mode that regards the transmission power of tie lines between systems as the black-start power supply. The starting power supply involved in the situation of the large power outage is incomplete and it is difficult to give full play to the respective advantages of internal and external power sources. In this paper, a method of coordinated black-start of large power grid internal and external power sources is proposed by combining the two modes. Firstly, the black-start capability evaluation system is built to screen out the internal black-start power supply, and the external black-start power supply is determined by analyzing the connection relationship between the systems. Then, based on the specific implementation principles, the black-start power supply coordination strategy is formulated by using the Dijkstra shortest path algorithm. Based on the condensation idea, the black-start zoning and path optimization method applicable to this strategy is proposed. Finally, the black-start security verification and corresponding control measures are adopted to obtain a scheme of black-start cooperation between internal and external power sources in the large power grid. The above method is applied in a real large power grid and compared with the conventional restoration strategy to verify the feasibility and efficiency of this method.

In recent times, Network-on-Chip (NoC) has become state of the art for communication in Multiprocessor System-on-Chip due to the existing scalability issues in this area. However, these systems are exposed to security threats such as extraction of secret information. Therefore, the need for secure communication arises in such environments. In this work, we present a communication protocol based on authenticated encryption with recovery mechanisms to establish secure end-to-end communication between the NoC nodes. In addition, a selected key agreement approach required for secure communication is implemented. The security functionality is located in the network adapter of each processing element. If data is tampered with or deleted during transmission, recovery mechanisms ensure that the corrupted data is retransmitted by the network adapter without the need of interference from the processing element. We simulated and implemented the complete system with SystemC TLM using the NoC simulation platform PANACA. Our results show that we can keep a high rate of correctly transmitted information even when attackers infiltrated the NoC system.

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%

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.

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

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.

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%.

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.

Highly secure devices are often isolated from the Internet or other public networks due to the confidential information they process. This level of isolation is referred to as an ’air-gap .’In this paper, we present a new technique named ETHERLED, allowing attackers to leak data from air-gapped networked devices such as PCs, printers, network cameras, embedded controllers, and servers. Networked devices have an integrated network interface controller (NIC) that includes status and activity indicator LEDs. We show that malware installed on the device can control the status LEDs by blinking and alternating colors, using documented methods or undocumented firmware commands. Information can be encoded via simple encoding such as Morse code and modulated over these optical signals. An attacker can intercept and decode these signals from tens to hundreds of meters away. We show an evaluation and discuss defensive and preventive countermeasures for this exfiltration attack.

This paper introduces a new type of attack on isolated, air-gapped workstations. Although air-gap computers have no wireless connectivity, we show that attackers can use the SATA cable as a wireless antenna to transfer radio signals at the 6 GHz frequency band. The Serial ATA (SATA) is a bus interface widely used in modern computers and connects the host bus to mass storage devices such as hard disk drives, optical drives, and solid-state drives. The prevalence of the SATA interface makes this attack highly available to attackers in a wide range of computer systems and IT environments. We discuss related work on this topic and provide technical background. We show the design of the transmitter and receiver and present the implementation of these components. We also demonstrate the attack on different computers and provide the evaluation. The results show that attackers can use the SATA cable to transfer a brief amount of sensitive information from highly secured, air-gap computers wirelessly to a nearby receiver. Furthermore, we show that the attack can operate from user mode, is effective even from inside a Virtual Machine (VM), and can successfully work with other running workloads in the background. Finally, we discuss defense and mitigation techniques for this new air-gap attack.