Grant: Discovery Grants Program - Individual
University of Manitoba
$32,000.00
Scalable, Reliable and Robust Provenance in the New Era of Interconnected Intelligent Systems
EF 2024-25
Résumé
The growing cost of cyberattacks is a global concern and is predicted to reach $8 trillion in 2023. To defend against cyberattacks, security analysts typically collect and analyze logged activities throughout the organizations. However, analyzing the collected logs can be a cumbersome and challenging task. Emerging technologies (such as Internet of Things (IoT)) and the advancements of Artificial Intelligence (AI) further increase the complexity of intelligent and interconnected computing systems and allow for more sophisticated attacks, which in turn hinder accurate and timely log analysis.
To address this, data provenance-based security mechanisms provide a promising solution. Data provenance captures causal dependencies between system activities using provenance graphs, and is widely leveraged to facilitate security analysis. However, effective provenance analysis in the new era of interconnected intelligent systems requires 1) scalable information retention mechanisms that can support today's cloud-scale systems, 2) reliability of provenance analysis results for threats spanning across interconnected lightweight devices and 3) robustness against evasive attacks disguising as normal user behaviors. Recent studies demonstrate that most existing provenance solutions have significant limitations in fulfilling such requirements.
My long-term research goal is to increase the transparency and trustworthiness of emerging interconnected AI-powered systems through developing a series of provenance-based security solutions. In the next 5 years, my group's effort will focus on the following three short-term objectives: RO1: to allow scalable provenance analysis, we will build a novel top-down approach for selective construction of the provenance graphs, intelligent summarization, and retaining only security-sensitive provenance information. RO2: to support reliable provenance analysis for interconnected lightweight IoT devices, we will leverage AI-based techniques to generate the missing logged information, detect, and explain attacks across different devices. RO3: to achieve more robust provenance analysis against evading attackers, we will combine Natural Language Processing (NLP) and AI techniques to detect deceptive events and morphing attacks.
The proposed research program will lead to novel and practical solutions for better understanding and mitigating various security threats in interconnected intelligent systems such as IoT and clouds. The added security protection of such systems will help enable their wider adoption as cost-effective and life-saving technologies, and thus provide significant financial and ethical benefits to our society. The proposed research will train 6 HQP over this 5-year term, and prepare them with both theoretic background and practical skills in cybersecurity, applied machine learning and real-world applications (e.g., IoT and clouds), which are among the most in-demand skills in both academia and industry.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Manitoba, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
RGPIN-2024-06414
Name nom
Tabiban, Azadeh
Department département
Computer Science
Organization id
19
Institution établissement
University of Manitoba
Province en
Manitoba
Province fr
Manitoba
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
32000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
803
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer communications
Area of application fr
Téléinformatique
Research subject code
2718
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Communication and information theory
Research subject fr
Théorie des télécommunications et de l'information
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Scalable, Reliable and Robust Provenance in the New Era of Interconnected Intelligent Systems
Keywords
provenance analysis; cloud/edge security; machine learning applied to security; internet of things (iot) security; network/nfv security
Application summary
The growing cost of cyberattacks is a global concern and is predicted to reach $8 trillion in 2023. To defend against cyberattacks, security analysts typically collect and analyze logged activities throughout the organizations. However, analyzing the collected logs can be a cumbersome and challenging task. Emerging technologies (such as Internet of Things (IoT)) and the advancements of Artificial Intelligence (AI) further increase the complexity of intelligent and interconnected computing systems and allow for more sophisticated attacks, which in turn hinder accurate and timely log analysis.
To address this, data provenance-based security mechanisms provide a promising solution. Data provenance captures causal dependencies between system activities using provenance graphs, and is widely leveraged to facilitate security analysis. However, effective provenance analysis in the new era of interconnected intelligent systems requires 1) scalable information retention mechanisms that can support today's cloud-scale systems, 2) reliability of provenance analysis results for threats spanning across interconnected lightweight devices and 3) robustness against evasive attacks disguising as normal user behaviors. Recent studies demonstrate that most existing provenance solutions have significant limitations in fulfilling such requirements.
My long-term research goal is to increase the transparency and trustworthiness of emerging interconnected AI-powered systems through developing a series of provenance-based security solutions. In the next 5 years, my group's effort will focus on the following three short-term objectives: RO1: to allow scalable provenance analysis, we will build a novel top-down approach for selective construction of the provenance graphs, intelligent summarization, and retaining only security-sensitive provenance information. RO2: to support reliable provenance analysis for interconnected lightweight IoT devices, we will leverage AI-based techniques to generate the missing logged information, detect, and explain attacks across different devices. RO3: to achieve more robust provenance analysis against evading attackers, we will combine Natural Language Processing (NLP) and AI techniques to detect deceptive events and morphing attacks.
The proposed research program will lead to novel and practical solutions for better understanding and mitigating various security threats in interconnected intelligent systems such as IoT and clouds. The added security protection of such systems will help enable their wider adoption as cost-effective and life-saving technologies, and thus provide significant financial and ethical benefits to our society. The proposed research will train 6 HQP over this 5-year term, and prepare them with both theoretic background and practical skills in cybersecurity, applied machine learning and real-world applications (e.g., IoT and clouds), which are among the most in-demand skills in both academia and industry.