Visible to the public Biblio

Found 12218 results

Submitted
Christopher Theisen, Brendan Murphy, Kim Herzig, Laurie Williams.  Submitted.  Risk-Based Attack Surface Approximation: How Much Data is Enough? International Conference on Software Engineering (ICSE) Software Engineering in Practice (SEIP) 2017.

Proactive security reviews and test efforts are a necessary component of the software development lifecycle. Resource limitations often preclude reviewing the entire code
base. Making informed decisions on what code to review can improve a team’s ability to find and remove vulnerabilities. Risk-based attack surface approximation (RASA) is a technique that uses crash dump stack traces to predict what code may contain exploitable vulnerabilities. The goal of this research is to help software development teams prioritize security efforts by the efficient development of a risk-based attack surface approximation. We explore the use of RASA using Mozilla Firefox and Microsoft Windows stack traces from crash dumps. We create RASA at the file level for Firefox, in which the 15.8% of the files that were part of the approximation contained 73.6% of the vulnerabilities seen for the product. We also explore the effect of random sampling of crashes on the approximation, as it may be impractical for organizations to store and process every crash received. We find that 10-fold random sampling of crashes at a rate of 10% resulted in 3% less vulnerabilities identified than using the entire set of stack traces for Mozilla Firefox. Sampling crashes in Windows 8.1 at a rate of 40% resulted in insignificant differences in vulnerability and file coverage as compared to a rate of 100%.

Ashiq Rahman, Ehab Al-Shaer.  Submitted.  Automated Synthesis of Resilient Network Access Controls: A Formal Framework with Refinement. IEEE Transactions of Parallel and Distributed Computing (TPDC),.

Due to the extensive use of network services and emerging security threats, enterprise networks deploy varieties of security devices for controlling resource access based on organizational security requirements. These requirements need fine-grained access control rules based on heterogeneous isolation patterns like access denial, trusted communication, and payload inspection. Organizations are also seeking for usable and optimal security configurations that can harden the network security within enterprise budget constraints. In order to design a security architecture, i.e., the distribution of security devices along with their security policies, that satisfies the organizational security requirements as well as the business constraints, it is required to analyze various alternative security architectures considering placements of network security devices in the network and the corresponding access controls. In this paper, we present an automated formal framework for synthesizing network security configurations. The main design alternatives include different kinds of isolation patterns for network traffic flows. The framework takes security requirements and business constraints along with the network topology as inputs. Then, it synthesizes cost-effective security configurations satisfying the constraints and provides placements of different security devices, optimally distributed in the network, according to the given network topology. In addition, we provide a hypothesis testing-based security architecture refinement mechanism that explores various security design alternatives using ConfigSynth and improves the security architecture by systematically increasing the security requirements. We demonstrate the execution of ConfigSynth and the refinement mechanism using case studies. Finally, we evaluate their scalability using simulated experiments.
 

[Anonymous].  Submitted.  Biblio title missing.
[Anonymous].  Submitted.  Natural Language Processing Characterization of Recurring Calls in Public Security Services.
Extracting knowledge from unstructured data silos, a legacy of old applications, is mandatory for improving the governance of today's cities and fostering the creation of smart cities. Texts in natural language often compose such data. Nevertheless, the inference of useful information from a linguistic-computational analysis of natural language data is an open challenge. In this paper, we propose a clustering method to analyze textual data employing the unsupervised machine learning algorithms k-means and hierarchical clustering. We assess different vector representation methods for text, similarity metrics, and the number of clusters that best matches the data. We evaluate the methods using a real database of a public record service of security occurrences. The results show that the k-means algorithm using Euclidean distance extracts non-trivial knowledge, reaching up to 93% accuracy in a set of test samples while identifying the 12 most prevalent occurrence patterns.
In Press
Ignacio X. Dominguez, Jayant Dhawan, Robert St. Amant, David L. Roberts.  In Press.  Exploring the Effects of Different Text Stimuli on Typing Behavior. International Conference on Cognitive Modeling.

In this work we explore how different cognitive processes af- fected typing patterns through a computer game we call The Typing Game. By manipulating the players’ familiarity with the words in our game through their similarity to dictionary words, and by allowing some players to replay rounds, we found that typing speed improves with familiarity with words, and also with practice, but that these are independent of the number of mistakes that are made when typing. We also found that users who had the opportunity to replay rounds exhibited different typing patterns even before replaying the rounds. 

Welk, A., Zielinska, O., Tembe, R., Xe, G., Hong, K. W., Murphy-Hill, E., Mayhorn, C. B..  In Press.  Will the “Phisher-men” Reel you in? Assessing Individual Differences in a Phishing Detection Task International Journal of Cyber Behavior, Psychology, and Learning. .

Phishing is an act of technology-based deception that targets individuals to obtain information. To minimize the number of phishing attacks, factors that influence the ability to identify phishing attempts must be examined. The present study aimed to determine how individual differences relate to performance on a phishing task. Undergraduate students completed a questionnaire designed to assess impulsivity, trust, personality characteristics, and Internet/security habits. Participants performed an email task where they had to discriminate between legitimate emails and phishing attempts. Researchers assessed performance in terms of correctly identifying all email types (overall accuracy) as well as accuracy in identifying phishing emails (phishing accuracy). Results indicated that overall and phishing accuracy each possessed unique trust, personality, and impulsivity predictors, but shared one significant behavioral predictor. These results present distinct predictors of phishing susceptibility that should be incorporated in the development of anti-phishing technology and training.

2021
Angermeir, Florian, Voggenreiter, Markus, Moyón, Fabiola, Mendez, Daniel.  2021.  Enterprise-Driven Open Source Software: A Case Study on Security Automation. 2021 IEEE/ACM 43rd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). :278—287.
Agile and DevOps are widely adopted by the industry. Hence, integrating security activities with industrial practices, such as continuous integration (CI) pipelines, is necessary to detect security flaws and adhere to regulators’ demands early. In this paper, we analyze automated security activities in CI pipelines of enterprise-driven open source software (OSS). This shall allow us, in the long-run, to better understand the extent to which security activities are (or should be) part of automated pipelines. In particular, we mine publicly available OSS repositories and survey a sample of project maintainers to better understand the role that security activities and their related tools play in their CI pipelines. To increase transparency and allow other researchers to replicate our study (and to take different perspectives), we further disclose our research artefacts.Our results indicate that security activities in enterprise-driven OSS projects are scarce and protection coverage is rather low. Only 6.83% of the analyzed 8,243 projects apply security automation in their CI pipelines, even though maintainers consider security to be rather important. This alerts industry to keep the focus on vulnerabilities of 3rd Party software and it opens space for other improvements of practice which we outline in this manuscript.
Pashchenko, Ivan, Scandariato, Riccardo, Sabetta, Antonino, Massacci, Fabio.  2021.  Secure Software Development in the Era of Fluid Multi-party Open Software and Services. 2021 IEEE/ACM 43rd International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER). :91—95.
Pushed by market forces, software development has become fast-paced. As a consequence, modern development projects are assembled from 3rd-party components. Security & privacy assurance techniques once designed for large, controlled updates over months or years, must now cope with small, continuous changes taking place within a week, and happening in sub-components that are controlled by third-party developers one might not even know they existed. In this paper, we aim to provide an overview of the current software security approaches and evaluate their appropriateness in the face of the changed nature in software development. Software security assurance could benefit by switching from a process-based to an artefact-based approach. Further, security evaluation might need to be more incremental, automated and decentralized. We believe this can be achieved by supporting mechanisms for lightweight and scalable screenings that are applicable to the entire population of software components albeit there might be a price to pay.
Plappert, Christian, Zelle, Daniel, Gadacz, Henry, Rieke, Roland, Scheuermann, Dirk, Krauß, Christoph.  2021.  Attack Surface Assessment for Cybersecurity Engineering in the Automotive Domain. 2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP). :266–275.
Connected smart cars enable new attacks that may have serious consequences. Thus, the development of new cars must follow a cybersecurity engineering process as defined for example in ISO/SAE 21434. A central part of such a process is the threat and risk assessment including an attack feasibility rating. In this paper, we present an attack surface assessment with focus on the attack feasibility rating compliant to ISO/SAE 21434. We introduce a reference architecture with assets constituting the attack surface, the attack feasibility rating for these assets, and the application of this rating on typical use cases. The attack feasibility rating assigns attacks and assets to an evaluation of the attacker dimensions such as the required knowledge and the feasibility of attacks derived from it. Our application of sample use cases shows how this rating can be used to assess the feasibility of an entire attack path. The attack feasibility rating can be used as a building block in a threat and risk assessment according to ISO/SAE 21434.
Wu, Xiaohe, Calderon, Juan, Obeng, Morrison.  2021.  Attribution Based Approach for Adversarial Example Generation. SoutheastCon 2021. :1–6.
Neural networks with deep architectures have been used to construct state-of-the-art classifiers that can match human level accuracy in areas such as image classification. However, many of these classifiers can be fooled by examples slightly modified from their original forms. In this work, we propose a novel approach for generating adversarial examples that makes use of only attribution information of the features and perturbs only features that are highly influential to the output of the classifier. We call this approach Attribution Based Adversarial Generation (ABAG). To demonstrate the effectiveness of this approach, three somewhat arbitrary algorithms are proposed and examined. In the first algorithm all non-zero attributions are utilized and associated features perturbed; in the second algorithm only the top-n most positive and top-n most negative attributions are used and corresponding features perturbed; and in the third algorithm the level of perturbation is increased in an iterative manner until an adversarial example is discovered. All of the three algorithms are implemented and experiments are performed on the well-known MNIST dataset. Experiment results show that adversarial examples can be generated very efficiently, and thus prove the validity and efficacy of ABAG - utilizing attributions for the generation of adversarial examples. Furthermore, as shown by examples, ABAG can be adapted to provides a systematic searching approach to generate adversarial examples by perturbing a minimum amount of features.
Lit, Yanyan, Kim, Sara, Sy, Eric.  2021.  A Survey on Amazon Alexa Attack Surfaces. 2021 IEEE 18th Annual Consumer Communications Networking Conference (CCNC). :1–7.
Since being launched in 2014, Alexa, Amazon's versatile cloud-based voice service, is now active in over 100 million households worldwide [1]. Alexa's user-friendly, personalized vocal experience offers customers a more natural way of interacting with cutting-edge technology by allowing the ability to directly dictate commands to the assistant. Now in the present year, the Alexa service is more accessible than ever, available on hundreds of millions of devices from not only Amazon but third-party device manufacturers. Unfortunately, that success has also been the source of concern and controversy. The success of Alexa is based on its effortless usability, but in turn, that has led to a lack of sufficient security. This paper surveys various attacks against Amazon Alexa ecosystem including attacks against the frontend voice capturing and the cloud backend voice command recognition and processing. Overall, we have identified six attack surfaces covering the lifecycle of Alexa voice interaction that spans several stages including voice data collection, transmission, processing and storage. We also discuss the potential mitigation solutions for each attack surface to better improve Alexa or other voice assistants in terms of security and privacy.
2020
Razin, Y. S., Feigh, K. M..  2020.  Hitting the Road: Exploring Human-Robot Trust for Self-Driving Vehicles. 2020 IEEE International Conference on Human-Machine Systems (ICHMS). :1—6.

With self-driving cars making their way on to our roads, we ask not what it would take for them to gain acceptance among consumers, but what impact they may have on other drivers. How they will be perceived and whether they will be trusted will likely have a major effect on traffic flow and vehicular safety. This work first undertakes an exploratory factor analysis to validate a trust scale for human-robot interaction and shows how previously validated metrics and general trust theory support a more complete model of trust that has increased applicability in the driving domain. We experimentally test this expanded model in the context of human-automation interaction during simulated driving, revealing how using these dimensions uncovers significant biases within human-robot trust that may have particularly deleterious effects when it comes to sharing our future roads with automated vehicles.

Susukailo, Vitalii, Opirskyy, Ivan, Vasylyshyn, Sviatoslav.  2020.  Analysis of the attack vectors used by threat actors during the pandemic. 2020 IEEE 15th International Conference on Computer Sciences and Information Technologies (CSIT). 2:261—264.

This article describes attacks methods, vectors and technics used by threat actors during pandemic situations in the world. Identifies common targets of threat actors and cyber-attack tactics. The article analyzes cybersecurity challenges and specifies possible solutions and improvements in cybersecurity. Defines cybersecurity controls, which should be taken against analyzed attack vectors.

Gillen, R. E., Carter, J. M., Craig, C., Johnson, J. A., Scott, S. L..  2020.  Assessing Anomaly-Based Intrusion Detection Configurations for Industrial Control Systems. 2020 IEEE 21st International Symposium on "A World of Wireless, Mobile and Multimedia Networks" (WoWMoM). :360—366.

To reduce cost and ease maintenance, industrial control systems (ICS) have adopted Ethernetbased interconnections that integrate operational technology (OT) systems with information technology (IT) networks. This integration has made these critical systems vulnerable to attack. Security solutions tailored to ICS environments are an active area of research. Anomalybased network intrusion detection systems are well-suited for these environments. Often these systems must be optimized for their specific environment. In prior work, we introduced a method for assessing the impact of various anomaly-based network IDS settings on security. This paper reviews the experimental outcomes when we applied our method to a full-scale ICS test bed using actual attacks. Our method provides new and valuable data to operators enabling more informed decisions about IDS configurations.

Stöckle, Patrick, Grobauer, Bernd, Pretschner, Alexander.  2020.  Automated Implementation of Windows-related Security-Configuration Guides. 2020 35th IEEE/ACM International Conference on Automated Software Engineering (ASE). :598—610.
Hardening is the process of configuring IT systems to ensure the security of the systems' components and data they process or store. The complexity of contemporary IT infrastructures, however, renders manual security hardening and maintenance a daunting task. In many organizations, security-configuration guides expressed in the SCAP (Security Content Automation Protocol) are used as a basis for hardening, but these guides by themselves provide no means for automatically implementing the required configurations. In this paper, we propose an approach to automatically extract the relevant information from publicly available security-configuration guides for Windows operating systems using natural language processing. In a second step, the extracted information is verified using the information of available settings stored in the Windows Administrative Template files, in which the majority of Windows configuration settings is defined. We show that our implementation of this approach can extract and implement 83% of the rules without any manual effort and 96% with minimal manual effort. Furthermore, we conduct a study with 12 state-of-the-art guides consisting of 2014 rules with automatic checks and show that our tooling can implement at least 97% of them correctly. We have thus significantly reduced the effort of securing systems based on existing security-configuration guides. In many organizations, security-configuration guides expressed in the SCAP (Security Content Automation Protocol) are used as a basis for hardening, but these guides by themselves provide no means for automatically implementing the required configurations. In this paper, we propose an approach to automatically extract the relevant information from publicly available security-configuration guides for Windows operating systems using natural language processing. In a second step, the extracted information is verified using the information of available settings stored in the Windows Administrative Template files, in which the majority of Windows configuration settings is defined. We show that our implementation of this approach can extract and implement 83% of the rules without any manual effort and 96% with minimal manual effort. Furthermore, we conduct a study with 12 state-of-the-art guides consisting of 2014 rules with automatic checks and show that our tooling can implement at least 97% of them correctly. We have thus significantly reduced the effort of securing systems based on existing security-configuration guides. In this paper, we propose an approach to automatically extract the relevant information from publicly available security-configuration guides for Windows operating systems using natural language processing. In a second step, the extracted information is verified using the information of available settings stored in the Windows Administrative Template files, in which the majority of Windows configuration settings is defined. We show that our implementation of this approach can extract and implement 83% of the rules without any manual effort and 96% with minimal manual effort. Furthermore, we conduct a study with 12 state-of-the-art guides consisting of 2014 rules with automatic checks and show that our tooling can implement at least 97% of them correctly. We have thus significantly reduced the effort of securing systems based on existing security-configuration guides. We show that our implementation of this approach can extract and implement 83% of the rules without any manual effort and 96% with minimal manual effort. Furthermore, we conduct a study with 12 state-of-the-art guides consisting of 2014 rules with automatic checks and show that our tooling can implement at least 97% of them correctly. We have thus significantly reduced the effort of securing systems based on existing security-configuration guides.
Badawi, E., Jourdan, G.-V., Bochmann, G., Onut, I.-V..  2020.  An Automatic Detection and Analysis of the Bitcoin Generator Scam. 2020 IEEE European Symposium on Security and Privacy Workshops (EuroS PW). :407—416.

We investigate what we call the "Bitcoin Generator Scam" (BGS), a simple system in which the scammers promise to "generate" new bitcoins using the ones that were sent to them. A typical offer will suggest that, for a small fee, one could receive within minutes twice the amount of bitcoins submitted. BGS is clearly not a very sophisticated attack. The modus operandi is simply to put up some web page on which to find the address to send the money and wait for the payback. The pages are then indexed by search engines, and ready to find for victims looking for free bitcoins. We describe here a generic system to find and analyze scams such as BGS. We have trained a classifier to detect these pages, and we have a crawler searching for instances using a series of search engines. We then monitor the instances that we find to trace payments and bitcoin addresses that are being used over time. Unlike most bitcoin-based scam monitoring systems, we do not rely on analyzing transactions on the blockchain to find scam instances. Instead, we proactively find these instances through the web pages advertising the scam. Thus our system is able to find addresses with very few transactions, or even none at all. Indeed, over half of the addresses that have eventually received funds were detected before receiving any transactions. The data for this paper was collected over four months, from November 2019 to February 2020. We have found more than 1,300 addresses directly associated with the scam, hosted on over 500 domains. Overall, these addresses have received (at least) over 5 million USD to the scam, with an average of 47.3 USD per transaction.

Abazar, T., Masjedi, P., Taheri, M..  2020.  A Binary Relevance Adaptive Model-Selection for Ensemble Steganalysis. 2020 17th International ISC Conference on Information Security and Cryptology (ISCISC). :77—81.

Steganalysis is an interesting classification problem in order to discriminate the images, including hidden messages from the clean ones. There are many methods, including deep CNN networks to extract fine features for this classification task. Nevertheless, a few researches have been conducted to improve the final classifier. Some state-of-the-art methods try to ensemble the networks by a voting strategy to achieve more stable performance. In this paper, a selection phase is proposed to filter improper networks before any voting. This filtering is done by a binary relevance multi-label classification approach. The Logistic Regression (LR) is chosen here as the last layer of network for classification. The large-margin Fisher’s linear discriminant (FLD) classifier is assigned to each one of the networks. It learns to discriminate the training instances which associated network is suitable for or not. Xu-Net, one of the most famous state-of-the-art Steganalysis models, is chosen as the base networks. The proposed method with different approaches is applied on the BOSSbase dataset and is compared with traditional voting and also some state-of-the-art related ensemble techniques. The results show significant accuracy improvement of the proposed method in comparison with others.

Yamaguchi, S..  2020.  Botnet Defense System and Its Basic Strategy Against Malicious Botnet. 2020 IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan). :1—2.

This paper proposes a basic strategy for Botnet Defense System (BDS). BDS is a cybersecurity system that utilizes white-hat botnets to defend IoT systems against malicious botnets. Once a BDS detects a malicious botnet, it launches white-hat worms in order to drive out the malicious botnet. The proposed strategy aims at the proper use of the worms based on the worms' capability such as lifespan and secondary infectivity. If the worms have high secondary infectivity or a long lifespan, the BDS only has to launch a few worms. Otherwise, it should launch as many worms as possible. The effectiveness of the strategy was confirmed through the simulation evaluation using agent-oriented Petri nets.

Nooh, Sameer A..  2020.  Cloud Cryptography: User End Encryption. 2020 International Conference on Computing and Information Technology (ICCIT-1441). :1—4.
Cloud computing has made the life of individual users and work of business corporations so much easier by providing them data storage services at very low costs. Individual users can store and access their data through shared cloud storage service anywhere anytime. Similarly, business corporation consumers of cloud computing can store, manage, process and access their big data with quite an ease. However, the security and privacy of users' data remains vulnerable in cloud computing Availability, integrity and confidentiality are the three primary elements that users consider before signing up for cloud computing services. Many public and private cloud services have experienced security breaches and unauthorized access incidents. This paper suggests user end cryptography of data before uploading it to a cloud storage service platform like Google Drive, Microsoft, Amazon and CloudSim etc. The proposed cryptography algorithm is based on symmetric key cryptography model and has been implemented on Amazon S3 cloud space service.
Xu, Hui, Zhang, Wei, Gao, Man, Chen, Hongwei.  2020.  Clustering Analysis for Big Data in Network Security Domain Using a Spark-Based Method. 2020 IEEE 5th International Symposium on Smart and Wireless Systems within the Conferences on Intelligent Data Acquisition and Advanced Computing Systems (IDAACS-SWS). :1—4.
Considering the problem of network security under the background of big data, the clustering analysis algorithms can be utilized to improve the correctness of network intrusion detection models for security management. As a kind of iterative clustering analysis algorithm, K-means algorithm is not only simple but also efficient, so it is widely used. However, the traditional K-means algorithm cannot well solve the network security problem when facing big data due to its high complexity and limited processing ability. In this case, this paper proposes to optimize the traditional K-means algorithm based on the Spark platform and deploy the optimized clustering analysis algorithm in the distributed architecture, so as to improve the efficiency of clustering algorithm for network intrusion detection in big data environment. The experimental result shows that, compared with the traditional K-means algorithm, the efficiency of the optimized K-means algorithm using a Spark-based method is significantly improved in the running time.
Kummerow, A., Monsalve, C., Rösch, D., Schäfer, K., Nicolai, S..  2020.  Cyber-physical data stream assessment incorporating Digital Twins in future power systems. 2020 International Conference on Smart Energy Systems and Technologies (SEST). :1—6.

Reliable and secure grid operations become more and more challenging in context of increasing IT/OT convergence and decreasing dynamic margins in today's power systems. To ensure the correct operation of monitoring and control functions in control centres, an intelligent assessment of the different information sources is necessary to provide a robust data source in case of critical physical events as well as cyber-attacks. Within this paper, a holistic data stream assessment methodology is proposed using an expert knowledge based cyber-physical situational awareness for different steady and transient system states. This approach goes beyond existing techniques by combining high-resolution PMU data with SCADA information as well as Digital Twin and AI based anomaly detection functionalities.

Javid, T., Faris, M., Beenish, H., Fahad, M..  2020.  Cybersecurity and Data Privacy in the Cloudlet for Preliminary Healthcare Big Data Analytics. 2020 International Conference on Computing and Information Technology (ICCIT-1441). :1—4.

In cyber physical systems, cybersecurity and data privacy are among most critical considerations when dealing with communications, processing, and storage of data. Geospatial data and medical data are examples of big data that require seamless integration with computational algorithms as outlined in Industry 4.0 towards adoption of fourth industrial revolution. Healthcare Industry 4.0 is an application of the design principles of Industry 4.0 to the medical domain. Mobile applications are now widely used to accomplish important business functions in almost all industries. These mobile devices, however, are resource poor and proved insufficient for many important medical applications. Resource rich cloud services are used to augment poor mobile device resources for data and compute intensive applications in the mobile cloud computing paradigm. However, the performance of cloud services is undesirable for data-intensive, latency-sensitive mobile applications due increased hop count between the mobile device and the cloud server. Cloudlets are virtual machines hosted in server placed nearby the mobile device and offer an attractive alternative to the mobile cloud computing in the form of mobile edge computing. This paper outlines cybersecurity and data privacy aspects for communications of measured patient data from wearable wireless biosensors to nearby cloudlet host server in order to facilitate the cloudlet based preliminary and essential complex analytics for the medical big data.

Elavarasan, G., Veni, S..  2020.  Data Sharing Attribute-Based Secure with Efficient Revocation in Cloud Computing. 2020 International Conference on Computing and Information Technology (ICCIT-1441). :1—6.

In recent days, cloud computing is one of the emerging fields. It is a platform to maintain the data and privacy of the users. To process and regulate the data with high security, the access control methods are used. The cloud environment always faces several challenges such as robustness, security issues and so on. Conventional methods like Cipher text-Policy Attribute-Based Encryption (CP-ABE) are reflected in providing huge security, but still, the problem exists like the non-existence of attribute revocation and minimum efficient. Hence, this research work particularly on the attribute-based mechanism to maximize efficiency. Initially, an objective coined out in this work is to define the attributes for a set of users. Secondly, the data is to be re-encrypted based on the access policies defined for the particular file. The re-encryption process renders information to the cloud server for verifying the authenticity of the user even though the owner is offline. The main advantage of this work evaluates multiple attributes and allows respective users who possess those attributes to access the data. The result proves that the proposed Data sharing scheme helps for Revocation under a fine-grained attribute structure.

Guo, Y., Wang, B., Hughes, D., Lewis, M., Sycara, K..  2020.  Designing Context-Sensitive Norm Inverse Reinforcement Learning Framework for Norm-Compliant Autonomous Agents. 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). :618—625.

Human behaviors are often prohibited, or permitted by social norms. Therefore, if autonomous agents interact with humans, they also need to reason about various legal rules, social and ethical social norms, so they would be trusted and accepted by humans. Inverse Reinforcement Learning (IRL) can be used for the autonomous agents to learn social norm-compliant behavior via expert demonstrations. However, norms are context-sensitive, i.e. different norms get activated in different contexts. For example, the privacy norm is activated for a domestic robot entering a bathroom where a person may be present, whereas it is not activated for the robot entering the kitchen. Representing various contexts in the state space of the robot, as well as getting expert demonstrations under all possible tasks and contexts is extremely challenging. Inspired by recent work on Modularized Normative MDP (MNMDP) and early work on context-sensitive RL, we propose a new IRL framework, Context-Sensitive Norm IRL (CNIRL). CNIRL treats states and contexts separately, and assumes that the expert determines the priority of every possible norm in the environment, where each norm is associated with a distinct reward function. The agent chooses the action to maximize its cumulative rewards. We present the CNIRL model and show that its computational complexity is scalable in the number of norms. We also show via two experimental scenarios that CNIRL can handle problems with changing context spaces.