AIGCN: Attack Intention Detection for Power System Using Graph Convolutional Networks

Tang, Qiuhang; Chen, Huadong; Ge, Binbin; Wang, Haoyu

doi:10.1007/s11265-021-01724-5

Cited by 3 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Q. Tang et al [35] present a method for detecting the attack intentions of malicious actors in power systems using graph convolutional networks (GCNs). Their proposed model, called Attack Intention Detection for Power System Using Graph Convolutional Networks (AIGCN), consists of two main steps.…”

Section: Deep Learningmentioning

confidence: 99%

“…• Contextualization: The need to recognize the context in which an action is performed, as it can affect the interpretation of the action. In digital forensics, the cybercrime context can provide valuable information about the intent of the actor [19,21,23,25,26,28,35]. • Missed activities, partial observability, or handling noise: The difficulty of recognizing an activity, and consequently intent, when only a part of it is observed or when some of the actions are totally missed.…”

Section: Challengesmentioning

confidence: 99%

“…It is common to encounter incomplete or partial data about cybercrime. This can make it difficult to recognize an attack or to determine the intent behind it [20,22,35]. • Predictive capabilities: The ability to predict future actions based on current observations.…”

Section: Challengesmentioning

confidence: 99%

“…• Managing multiple hypotheses: Different IR models generate multiple hypotheses about the intent of the agent based on the observed activities. It is important to manage these hypotheses and select the most plausible one by evaluating them based on the available evidence [21,35]. • Multi-step attack: nowadays, attackers instead of attacking immediately, build their attack through time by advancing step by step.…”

Section: Challengesmentioning

confidence: 99%

“…• Adversarial agents: Such agents can intentionally try to mislead the recognition system by performing actions that are inconsistent with their true intentions [10,11,[21][22][23]27,29]. • Understanding the attacker's ability and belief: This can help in predicting their future actions and identifying potential vulnerabilities [22,30,35]. • Lack of standard intent classification: This makes it difficult to compare and evaluate different intent recognition systems [10,11,[21][22][23].…”

Section: Challengesmentioning

confidence: 99%

See 4 more Smart Citations

Intention Recognition in Digital Forensics: Systematic Review

Kassa,

James,

Belay

2024

Preprint

View full text Add to dashboard Cite

In this comprehensive review, we delve into the realm of intention recognition within the context of digital forensics and cybercrime. The rise of cybercrime has become a major concern for individuals, organizations, and governments worldwide. Digital forensics is a field that deals with the investigation and analysis of digital evidence in order to identify, preserve, and analyze information that can be used as evidence in a court of law. Whereas, Intention recognition is a subfield of artificial intelligence that deals with the identification of agents’ intentions based on their actions and change of states. In the context of cybercrime, intention recognition can be used to identify the intentions of cybercriminals and even to predict their future actions. Employing a meticulous six-step systematic review approach, we curated research articles from reputable journals and categorized them into three distinct modeling approaches: logic-based, classical machine learning-based, and deep learning-based. Notably, intention recognition has transcended its historical confinement to network security, now addressing critical challenges across various subdomains, including social engineering attacks, AI black box vulnerabilities, and physical security. While deep learning emerges as the dominant paradigm, its inherent lack of transparency poses unique challenges in the digital forensics landscape. We advocate for hybrid solutions that blend deep learning’s power with interpretability. Furthermore, we propose the creation of a comprehensive taxonomy to precisely define intention recognition, paving the way for future advancements in this pivotal field.

show abstract

Section: Deep Learningmentioning

confidence: 99%

Section: Challengesmentioning

confidence: 99%

Section: Challengesmentioning

confidence: 99%

Section: Challengesmentioning

confidence: 99%

Section: Challengesmentioning

confidence: 99%

See 3 more Smart Citations

Intention Recognition in Digital Forensics: Systematic Review

Kassa,

James,

Belay

2024

Preprint

View full text Add to dashboard Cite

show abstract

Web Attack Payload Identification and Interpretability Analysis Based on Graph Convolutional Network

Fang

Liu

2022

2022 18th International Conference on Mobility, Sensing and Networking (MSN)

View full text Add to dashboard Cite

Cybercrime Intention Recognition: A Systematic Literature Review

Kassa,

James,

Belay

2024

Information

View full text Add to dashboard Cite

In this systematic literature review, we delve into the realm of intention recognition within the context of digital forensics and cybercrime. The rise of cybercrime has become a major concern for individuals, organizations, and governments worldwide. Digital forensics is a field that deals with the investigation and analysis of digital evidence in order to identify, preserve, and analyze information that can be used as evidence in a court of law. Intention recognition is a subfield of artificial intelligence that deals with the identification of agents’ intentions based on their actions and change of states. In the context of cybercrime, intention recognition can be used to identify the intentions of cybercriminals and even to predict their future actions. Employing a PRISMA systematic review approach, we curated research articles from reputable journals and categorized them into three distinct modeling approaches: logic-based, classical machine learning-based, and deep learning-based. Notably, intention recognition has transcended its historical confinement to network security, now addressing critical challenges across various subdomains, including social engineering attacks, artificial intelligence black box vulnerabilities, and physical security. While deep learning emerges as the dominant paradigm, its inherent lack of transparency poses a challenge in the digital forensics landscape. However, it is imperative that models developed for digital forensics possess intrinsic attributes of explainability and logical coherence, thereby fostering judicial confidence, mitigating biases, and upholding accountability for their determinations. To this end, we advocate for hybrid solutions that blend explainability, reasonableness, efficiency, and accuracy. Furthermore, we propose the creation of a taxonomy to precisely define intention recognition, paving the way for future advancements in this pivotal field.

show abstract

AIGCN: Attack Intention Detection for Power System Using Graph Convolutional Networks

Cited by 3 publications

References 30 publications

Intention Recognition in Digital Forensics: Systematic Review

Intention Recognition in Digital Forensics: Systematic Review

Web Attack Payload Identification and Interpretability Analysis Based on Graph Convolutional Network

Cybercrime Intention Recognition: A Systematic Literature Review

Contact Info

Product

Resources

About