Open Access. Powered by Scholars. Published by Universities.®

Information Security Commons™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 1561 - 1590 of 4669

Full-Text Articles in Information Security

A Framework For Identifying Host-Based Artifacts In Dark Web Investigations, Arica Kulm Nov 2020

A Framework For Identifying Host-Based Artifacts In Dark Web Investigations, Arica Kulm

Masters Theses & Doctoral Dissertations

The dark web is the hidden part of the internet that is not indexed by search engines and is only accessible with a specific browser like The Onion Router (Tor). Tor was originally developed as a means of secure communications and is still used worldwide for individuals seeking privacy or those wanting to circumvent restrictive regimes. The dark web has become synonymous with nefarious and illicit content which manifests itself in underground marketplaces containing illegal goods such as drugs, stolen credit cards, stolen user credentials, child pornography, and more (Kohen, 2017). Dark web marketplaces contribute both to illegal drug usage …


Establishing Blockchain-Related Security Controls, Maitha Ali Al Ketbi Nov 2020

Establishing Blockchain-Related Security Controls, Maitha Ali Al Ketbi

Theses

Blockchain technology is a secure and relatively new technology of distributed digital ledgers which is based on interlinked blocks of transactions. There is a rapid growth in the adoption of the blockchain technology in different solutions and applications and within different industries throughout the world, such as but not limited to, finance, supply chain, digital identity, energy, healthcare, real estate and government. Blockchain technology has great benefits such as decentralization, transparency, immutability and automation. Like any other emerging technology, the blockchain technology has also several risks and threats associated with its expected benefits which in turns could have a negative …


A Secure Flexible And Tampering-Resistant Data Sharing System For Vehicular Social Networks, Jianfei Sun, Hu Xiong, Shufan Zhang, Ximeng Liu, Jiaming Yuan, Robert H. Deng Nov 2020

A Secure Flexible And Tampering-Resistant Data Sharing System For Vehicular Social Networks, Jianfei Sun, Hu Xiong, Shufan Zhang, Ximeng Liu, Jiaming Yuan, Robert H. Deng

Research Collection School Of Computing and Information Systems

Vehicular social networks (VSNs) have emerged as the promising paradigm of vehicular networks that can improve traffic safety, relieve traffic congestion and even provide comprehensive social services by sharing vehicular sensory data. To selectively share the sensory data with other vehicles in the vicinity and reduce the local storage burden of vehicles, the vehicular sensory data are usually outsourced to vehicle cloud server for sharing and searching. However, existing data sharing systems for VSNs can neither provide secure selective one-to-many data sharing and verifiable data retrieval over encrypted data nor ensure that the integrity of retrieved data. In this paper, …


Multi-User Verifiable Searchable Symmetric Encryption For Cloud Storage, Xueqiao Liu, Guomin Yang, Guomin Yang Nov 2020

Multi-User Verifiable Searchable Symmetric Encryption For Cloud Storage, Xueqiao Liu, Guomin Yang, Guomin Yang

Research Collection School Of Computing and Information Systems

In a cloud data storage system, symmetric key encryption is usually used to encrypt files due to its high efficiency. In order allow the untrusted/semi-trusted cloud storage server to perform searching over encrypted data while maintaining data confidentiality, searchable symmetric encryption (SSE) has been proposed. In a typical SSE scheme, a users stores encrypted files on a cloud storage server and later can retrieve the encrypted files containing specific keywords. The basic security requirement of SSE is that the cloud server learns no information about the files or the keywords during the searching process. Some SSE schemes also offer additional …


A Tripartite Model Of Trust In Facebook: Acceptance Of Information Personalization, Privacy Concern, And Privacy Literacy, Sonny Rosenthal, Ole-Christian Wasenden, Gorm-Andreas Gronnevet, Rich Ling Nov 2020

A Tripartite Model Of Trust In Facebook: Acceptance Of Information Personalization, Privacy Concern, And Privacy Literacy, Sonny Rosenthal, Ole-Christian Wasenden, Gorm-Andreas Gronnevet, Rich Ling

Research Collection College of Integrative Studies

This study draws on the mental accounting perspective and a tripartite model of trust to explain why users trust Facebook. We argue that trust in Facebook is related to (1) trust in companies that collect personal data, (2) acceptance of information personalization, (3) low privacy concern, and (4) low privacy literacy. Further, we argue that privacy literacy amplifies the relationship between privacy concern and the other factors. This is because, among individuals with high privacy literacy, privacy concern is especially diagnostic of the potential harms of a loss of privacy. These arguments align broadly with theorizations about factors influencing privacy-related …


Coinwatch: A Clone-Based Approach For Detecting Vulnerabilities In Cryptocurrencies, Qingze Hum, Wei Jin Tan, Shi Ying Tey, Latasha Lenus, Ivan Homoliak, Yun Lin, Jun Sun Nov 2020

Coinwatch: A Clone-Based Approach For Detecting Vulnerabilities In Cryptocurrencies, Qingze Hum, Wei Jin Tan, Shi Ying Tey, Latasha Lenus, Ivan Homoliak, Yun Lin, Jun Sun

Research Collection School Of Computing and Information Systems

Cryptocurrencies have become very popular in recent years. Thousands of new cryptocurrencies have emerged, proposing new and novel techniques that improve on Bitcoin's core innovation of the blockchain data structure and consensus mechanism. However, cryptocurrencies are a major target for cyber-attacks, as they can be sold on exchanges anonymously and most cryptocurrencies have their codebases publicly available. One particular issue is the prevalence of code clones in cryptocurrencies, which may amplify security threats. If a vulnerability is found in one cryptocurrency, it might be propagated into other cloned cryptocurrencies. In this work, we propose a systematic remedy to this problem, …


Sfuzz: An Efficient Adaptive Fuzzer For Solidity Smart Contracts, Tai D. Nguyen, Long H. Pham, Jun Sun, Yun Lin, Minh Quang Tran Nov 2020

Sfuzz: An Efficient Adaptive Fuzzer For Solidity Smart Contracts, Tai D. Nguyen, Long H. Pham, Jun Sun, Yun Lin, Minh Quang Tran

Research Collection School Of Computing and Information Systems

Smart contracts are Turing-complete programs that execute on the infrastructure of the blockchain, which often manage valuable digital assets. Solidity is one of the most popular programming languages for writing smart contracts on the Ethereum platform. Like traditional programs, smart contracts may contain vulnerabilities. Unlike traditional programs, smart contracts cannot be easily patched once they are deployed. It is thus important that smart contracts are tested thoroughly before deployment. In this work, we present an adaptive fuzzer for smart contracts on the Ethereum platform called sFuzz. Compared to existing Solidity fuzzers, sFuzz combines the strategy in the AFL fuzzer and …


Boosting Privately: Federated Extreme Gradient Boosting For Mobile Crowdsensing, Yang Liu, Zhuo Ma, Ximeng Liu, Siqi Ma, Surya Nepal, Robert H. Deng, Kui Ren Nov 2020

Boosting Privately: Federated Extreme Gradient Boosting For Mobile Crowdsensing, Yang Liu, Zhuo Ma, Ximeng Liu, Siqi Ma, Surya Nepal, Robert H. Deng, Kui Ren

Research Collection School Of Computing and Information Systems

Recently, Google and other 24 institutions proposed a series of open challenges towards federated learning (FL), which include application expansion and homomorphic encryption (HE). The former aims to expand the applicable machine learning models of FL. The latter focuses on who holds the secret key when applying HE to FL. For the naive HE scheme, the server is set to master the secret key. Such a setting causes a serious problem that if the server does not conduct aggregation before decryption, a chance is left for the server to access the user’s update. Inspired by the two challenges, we propose …


Attribute-Based Keyword Search Over Hierarchical Data In Cloud Computing, Yinbin Miao, Jianfeng Ma, Ximeng Liu, Xinghua Li, Qi Jiang, Junwei Zhang Nov 2020

Attribute-Based Keyword Search Over Hierarchical Data In Cloud Computing, Yinbin Miao, Jianfeng Ma, Ximeng Liu, Xinghua Li, Qi Jiang, Junwei Zhang

Research Collection School Of Computing and Information Systems

Searchable encryption (SE) has been a promising technology which allows users to perform search queries over encrypted data. However, the most of existing SE schemes cannot deal with the shared records that have hierarchical structures. In this paper, we devise a basic cryptographic primitive called as attribute-based keyword search over hierarchical data (ABKS-HD) scheme by using the ciphertext-policy attribute-based encryption (CP-ABE) technique, but this basic scheme cannot satisfy all the desirable requirements of cloud systems. The facts that the single keyword search will yield many irrelevant search results and the revoked users can access the unauthorized data with the old …


International Conference Information Systems And Security, University For Business And Technology - Ubt Oct 2020

International Conference Information Systems And Security, University For Business And Technology - Ubt

UBT International Conference

UBT Annual International Conference is the 9th international interdisciplinary peer reviewed conference which publishes works of the scientists as well as practitioners in the area where UBT is active in Education, Research and Development. The UBT aims to implement an integrated strategy to establish itself as an internationally competitive, research-intensive university, committed to the transfer of knowledge and the provision of a world-class education to the most talented students from all background. The main perspective of the conference is to connect the scientists and practitioners from different disciplines in the same place and make them be aware of the recent …


Towards Increasing Trust In Expert Evidence Derived From Malware Forensic Tools, Ian M. Kennedy, Blaine Price, Arosha Bandara Oct 2020

Towards Increasing Trust In Expert Evidence Derived From Malware Forensic Tools, Ian M. Kennedy, Blaine Price, Arosha Bandara

Journal of Digital Forensics, Security and Law

Following a series of high profile miscarriages of justice in the UK linked to questionable expert evidence, the post of the Forensic Science Regulator was created in 2008. The main objective of this role is to improve the standard of practitioner competences and forensic procedures. One of the key strategies deployed to achieve this is the push to incorporate a greater level of scientific conduct in the various fields of forensic practice. Currently there is no statutory requirement for practitioners to become accredited to continue working with the Criminal Justice System of England and Wales. However, the Forensic Science Regulator …


A Forensic First Look At A Pos Device: Searching For Pci Dss Data Storage Violations, Stephen Larson, James Jones, Jim Swauger Oct 2020

A Forensic First Look At A Pos Device: Searching For Pci Dss Data Storage Violations, Stephen Larson, James Jones, Jim Swauger

Journal of Digital Forensics, Security and Law

According to the Verizon 2018 Data Breach Investigations Report, 321 POS terminals (user devices) were involved in about 14% of the 2,216 data breaches in 2017 (Verizon, 2018). These data breaches involved standalone POS terminals as well as associated controller systems. This paper examines a standalone Point-of-Sale (POS) system which is ubiquitous in smaller retail stores and restaurants. An attempt to extract unencrypted data and identify possible violations of the Payment Card Industry Data Security Standard (PCI DSS) requirement to protect stored cardholder data were be made. Persistent storage (flash memory chips) were removed from the devices and their contents …


Contingency Planning Amidst A Pandemic, Natalie C. Belford Oct 2020

Contingency Planning Amidst A Pandemic, Natalie C. Belford

KSU Proceedings on Cybersecurity Education, Research and Practice

Proper prior planning prevents pitifully poor performance: The purpose of this research is to address mitigation approaches - disaster recovery, contingency planning, and continuity planning - and their benefits as they relate to university operations during a worldwide pandemic predicated by the Novel Coronavirus (COVID-19). The most relevant approach pertaining to the University’s needs and its response to the Coronavirus pandemic will be determined and evaluated in detail.


Developing An Ai-Powered Chatbot To Support The Administration Of Middle And High School Cybersecurity Camps, Jonathan He, Chunsheng Xin Oct 2020

Developing An Ai-Powered Chatbot To Support The Administration Of Middle And High School Cybersecurity Camps, Jonathan He, Chunsheng Xin

KSU Proceedings on Cybersecurity Education, Research and Practice

Throughout the Internet, many chatbots have been deployed by various organizations to answer questions asked by customers. In recent years, we have been running cybersecurity summer camps for youth. Due to COVID-19, our in-person camp has been changed to virtual camps. As a result, we decided to develop a chatbot to reduce the number of emails, phone calls, as well as the human burden for answering the same or similar questions again and again based on questions we received from previous camps. This paper introduces our practical experience to implement an AI-powered chatbot for middle and high school cybersecurity camps …


A Survey Of Serious Games For Cybersecurity Education And Training, Winston Anthony Hill Jr., Mesafint Fanuel, Xiaohong Yuan, Jinghua Zhang, Sajad Sajad Oct 2020

A Survey Of Serious Games For Cybersecurity Education And Training, Winston Anthony Hill Jr., Mesafint Fanuel, Xiaohong Yuan, Jinghua Zhang, Sajad Sajad

KSU Proceedings on Cybersecurity Education, Research and Practice

Serious games can challenge users in competitive and entertaining ways. Educators have used serious games to increase student engagement in cybersecurity education. Serious games have been developed to teach students various cybersecurity topics such as safe online behavior, threats and attacks, malware, and more. They have been used in cybersecurity training and education at different levels. Serious games have targeted different audiences such as K-12 students, undergraduate and graduate students in academic institutions, and professionals in the cybersecurity workforce. In this paper, we provide a survey of serious games used in cybersecurity education and training. We categorize these games into …


Factors That Influence Hipaa Secure Compliance In Small And Medium-Size Health Care Facilities, Wlad Pierre-Francois, Indira Guzman Oct 2020

Factors That Influence Hipaa Secure Compliance In Small And Medium-Size Health Care Facilities, Wlad Pierre-Francois, Indira Guzman

KSU Proceedings on Cybersecurity Education, Research and Practice

This study extends the body of literature concerning security compliance by investigating the antecedents of HIPPA security compliance. A conceptual model, specifying a set of hypothesized relationships between management support, security awareness, security culture; security behavior, and risk of sanctions to address their effect on HIPAA security compliance is presented. This model was developed based on the review of the literature, Protection Motivation Theory, and General Deterrence Theory. Specifically, the aim of the study is to examine the mediating role of risk of sanctions on HIPAA security compliance.


Towards An Assessment Of Pause Periods On User Habituation In Mitigation Of Phishing Attacks, Amy Antonucci, Yair Levy, Martha Snyder, Laurie Dringus Oct 2020

Towards An Assessment Of Pause Periods On User Habituation In Mitigation Of Phishing Attacks, Amy Antonucci, Yair Levy, Martha Snyder, Laurie Dringus

KSU Proceedings on Cybersecurity Education, Research and Practice

Social engineering is the technique in which the attacker sends messages to build a relationship with the victim and convinces the victim to take some actions that lead to significant damages and losses. Industry and law enforcement reports indicate that social engineering incidents costs organizations billions of dollars. Phishing is the most pervasive social engineering attack. While email filtering and warning messages have been implemented for over three decades, organizations are constantly falling for phishing attacks. Prior research indicated that attackers use phishing emails to create an urgency and fear response in their victims causing them to use quick heuristics, …


Towards An Assessment Of Judgment Errors In Social Engineering Attacks Due To Environment And Device Type, Tommy Pollock, Yair Levy, Wei Li, Ajoy Kumar Oct 2020

Towards An Assessment Of Judgment Errors In Social Engineering Attacks Due To Environment And Device Type, Tommy Pollock, Yair Levy, Wei Li, Ajoy Kumar

KSU Proceedings on Cybersecurity Education, Research and Practice

Phishing continues to be a significant invasive threat to computer and mobile device users. Cybercriminals continuously develop new phishing schemes using email, and malicious search engine links to gather personal information of unsuspecting users. This information is used for financial gains through identity theft schemes or draining financial accounts of victims. Users are often distracted and fail to fully process the phishing attacks then unknowingly fall victim to the scam until much later. Users operating mobile phones and computers are likely to make judgment errors when making decisions in distracting environments due to cognitive overload. Distracted users can fail to …


Cybersecurity Strategy Against Cyber Attacks Towards Smart Grids With Pvs, Fangyu Li, Maria Valero, Liang Zhao, Yousef Mahmoud Oct 2020

Cybersecurity Strategy Against Cyber Attacks Towards Smart Grids With Pvs, Fangyu Li, Maria Valero, Liang Zhao, Yousef Mahmoud

KSU Proceedings on Cybersecurity Education, Research and Practice

Cyber attacks threaten the security of distribution power grids, such as smart grids. The emerging renewable energy sources such as photovoltaics (PVs) with power electronics controllers introduce new potential vulnerabilities. Based on the electric waveform data measured by waveform sensors in the smart grids, we propose a novel cyber attack detection and identification approach. Firstly, we analyze the cyber attack impacts (including cyber attacks on the solar inverter causing unusual harmonics) on electric waveforms in distribution power grids. Then, we propose a novel deep learning based mechanism including attack detection and attack diagnosis. By leveraging the electric waveform sensor data …


Espade: An Efficient And Semantically Secure Shortest Path Discovery For Outsourced Location-Based Services, Bharath K. Samanthula, Divyadharshini Karthikeyan, Boxiang Dong, K. Anitha Kumari Oct 2020

Espade: An Efficient And Semantically Secure Shortest Path Discovery For Outsourced Location-Based Services, Bharath K. Samanthula, Divyadharshini Karthikeyan, Boxiang Dong, K. Anitha Kumari

Department of Computer Science Faculty Scholarship and Creative Works

With the rapid growth of smart devices and technological advancements in tracking geospatial data, the demand for Location-Based Services (LBS) is facing a constant rise in several domains, including military, healthcare and transportation. It is a natural step to migrate LBS to a cloud environment to achieve on-demand scalability and increased resiliency. Nonetheless, outsourcing sensitive location data to a third-party cloud provider raises a host of privacy concerns as the data owners have reduced visibility and control over the outsourced data. In this paper, we consider outsourced LBS where users want to retrieve map directions without disclosing their location information. …


A Partition Based Feature Selection Approach For Mixed Data Clustering, Ashish Dutt Oct 2020

A Partition Based Feature Selection Approach For Mixed Data Clustering, Ashish Dutt

Student Works (2020-2029)

Presently, educational institutions compile and store huge volumes of data, such as student enrolment and attendance records, as well as their examination results. Mining such data yields stimulating information that serves its handlers well. Rapid growth in educational data points to the fact that distilling massive amounts of data requires a more sophisticated set of algorithms. This issue led to the emergence of the field of Educational Data Mining (EDM). Traditional data mining algorithms cannot be directly applied to educational problems, as they may have a specific objective and function. This implies that a pre-processing algorithm has to be enforced …


Enhancing A Cluster-Based Tdma Mac Protocol For Vehicle-To-Vehicle Communications, Abubakar Bello Tambawal Oct 2020

Enhancing A Cluster-Based Tdma Mac Protocol For Vehicle-To-Vehicle Communications, Abubakar Bello Tambawal

Student Works (2020-2029)

Vehicular Ad hoc Network technology (VANET) is one of the emerging and promising wireless technology, providing support for vehicles to communicate and share resources, (such as safety messages) through vehicle-to-vehicle (V2V) communications. Sequel to that the Time Division Multiple Access (TDMA) MAC protocol using a cluster-based topology has been proposed by the research community. Most of the existing research works focused on the cluster head (CH) election with very few addressing other critical issues, including cluster formation, efficient time slot allocation, and cluster maintenance. These challenges result in an unstable cluster, which could affect the timely delivery of safety applications. …


Rethinking The Weakness Of Stream Ciphers And Its Application To Encrypted Malware Detection, William Stone, Daeyoung Kim, Victor Youdom Kemmoe, Mingon Kang, Junggab Son Oct 2020

Rethinking The Weakness Of Stream Ciphers And Its Application To Encrypted Malware Detection, William Stone, Daeyoung Kim, Victor Youdom Kemmoe, Mingon Kang, Junggab Son

School of Computing Faculty Scholarship and Creative Works

One critical vulnerability of stream ciphers is the reuse of an encryption key. Since most stream ciphers consist of only a key scheduling algorithm and an Exclusive OR (XOR) operation, an adversary may break the cipher by XORing two captured ciphertexts generated under the same key. Various cryptanalysis techniques based on this property have been introduced in order to recover plaintexts or encryption keys; in contrast, this research reinterprets the vulnerability as a method of detecting stream ciphers from the ciphertexts it generates. Patterns found in the values (characters) expressed across the bytes of a ciphertext make the ciphertext distinguishable …


قبول المعلومات الأمنية وردها في ضوء مناهج المحدثين, Hicham Almaghari Oct 2020

قبول المعلومات الأمنية وردها في ضوء مناهج المحدثين, Hicham Almaghari

Al Jinan الجنان

عالج الباحث الموضوع في مبحثين: قدّم في الأول تعريف المعلومة الأمنية لغة واصطلاحا، وأشار إلى مجالات النشاط الاستخباري بشكل عام، ثم عرّف المعلومة الأمنية، وأصل في المبحث الثاني طرققبول المعلومة الأمنية وردها مستفيدا من مناهج المحدثين. اتبع الباحث المنهج الوصفي بغرض التعريف بالأمن والمعلومات، وتتبع منهج المحدثين في قبول ورد الرواية، كما اتبع المنهج التحليلي في مقاربة طرق المحدثين عند قبولهم أو ردهم للرواية، ومقارنة ذلك مع المعلومة الأمنية للوصول إلى النتائج المرجوة . توصل الباحث إلى وجود كثير من القواسم المشتركة بين صناعة المعلومة الأمنية ومنهج المدثين في التعاطي مع الرواية. خلص الباحث إلى ضرورة الاستفادة من مناهج المحدّثين …


Integrated Cyberattack Detection And Resilient Control Strategies Using Lyapunov-Based Economic Model Predictive Control, Henrique Oyama, Helen Durand Oct 2020

Integrated Cyberattack Detection And Resilient Control Strategies Using Lyapunov-Based Economic Model Predictive Control, Henrique Oyama, Helen Durand

Chemical Engineering and Materials Science Faculty Research Publications

The use of an integrated system framework, characterized by numerous cyber/physical components (sensor measurements, signals to actuators) connected through wired/wireless networks, has not only increased the ability to control industrial systems, but also the vulnerabilities to cyberattacks. State measurement cyberattacks could pose threats to process control systems since feedback control may be lost if the attack policy is not thwarted. Motivated by this, we propose three detection concepts based on Lyapunov‐based economic model predictive control (LEMPC) for nonlinear systems. The first approach utilizes randomized modifications to an LEMPC formulation online to potentially detect cyberattacks. The second method detects attacks when …


A Survey On Securing Personally Identifiable Information On Smartphones, Dar’Rell Pope, Yen-Hung (Frank) Hu, Mary Ann Hoppa Oct 2020

A Survey On Securing Personally Identifiable Information On Smartphones, Dar’Rell Pope, Yen-Hung (Frank) Hu, Mary Ann Hoppa

Virginia Journal of Science

With an ever-increasing footprint, already topping 3 billion devices, smartphones have become a huge cybersecurity concern. The portability of smartphones makes them convenient for users to access and store personally identifiable information (PII); this also makes them a popular target for hackers. This survey shares practical insights derived from analyzing 16 real-life case studies that exemplify: the vulnerabilities that leave smartphones open to cybersecurity attacks; the mechanisms and attack vectors typically used to steal PII from smartphones; the potential impact of PII breaches upon all parties involved; and recommended defenses to help prevent future PII losses. The contribution of this …


The Hidden Advantage Among Digital Natives Within Bug Bounty Programs, James (Jimmy) Allah-Mensah Oct 2020

The Hidden Advantage Among Digital Natives Within Bug Bounty Programs, James (Jimmy) Allah-Mensah

Cybersecurity Undergraduate Research Showcase

Bug bounty programs are a great way for companies and organizations to help keep their systems and information secure; however, there are only a limited number of white hat hacking participant spots. With only so many seats available at the table, being able to determine the most qualified group of individuals is critical to the efficiency of the program at large. Digital natives, people born into the digital age, provide an instinctive approach when dealing with technology. On the other hand, digital immigrants, people who grew up before the digital age and had to adapt to new technology, evidently utilize …


The Internet Never Forgets: Image-Based Sexual Abuse And The Workplace, John Schriner, Melody Lee Rood Oct 2020

The Internet Never Forgets: Image-Based Sexual Abuse And The Workplace, John Schriner, Melody Lee Rood

Publications and Research

Image-based sexual abuse (IBSA), commonly known as revenge pornography, is a type of cyberharassment that often results in detrimental effects to an individual's career and livelihood. Although there exists valuable research concerning cyberharassment in the workplace generally, there is little written about specifically IBSA and the workplace. This chapter examines current academic research on IBSA, the issues with defining this type of abuse, victim blaming, workplace policy, and challenges to victim-survivors' redress. The authors explore monetary motivation for websites that host revenge pornography and unpack how the dark web presents new challenges to seeking justice. Additionally, this chapter presents recommendations …


White-Box Fairness Testing Through Adversarial Sampling, Peixin Zhang, Jingyi Wang, Jun Sun, Guoliang Dong, Xinyu Wang, Xingen Wang, Jin Song Dong, Dai Ting Oct 2020

White-Box Fairness Testing Through Adversarial Sampling, Peixin Zhang, Jingyi Wang, Jun Sun, Guoliang Dong, Xinyu Wang, Xingen Wang, Jin Song Dong, Dai Ting

Research Collection School Of Computing and Information Systems

Although deep neural networks (DNNs) have demonstrated astonishing performance in many applications, there are still concerns on their dependability. One desirable property of DNN for applications with societal impact is fairness (i.e., non-discrimination). In this work, we propose a scalable approach for searching individual discriminatory instances of DNN. Compared with state-of-the-art methods, our approach only employs lightweight procedures like gradient computation and clustering, which makes it significantly more scalable than existing methods. Experimental results show that our approach explores the search space more effectively (9 times) and generates much more individual discriminatory instances (25 times) using much less time (half …


Lecture - Csci 275: Linux Systems Administration And Security, Moe Hassan, Nyc Tech-In-Residence Corps Oct 2020

Lecture - Csci 275: Linux Systems Administration And Security, Moe Hassan, Nyc Tech-In-Residence Corps

Open Educational Resources

Lecture for CSCI 275: Linux Systems Administration and Security