Explainable Artificial Intelligence (XAI): Connecting Artificial Decision-Making and Human Trust in Autonomous Vehicles

Madhav, A. V. Shreyas; Tyagi, Amit Kumar

doi:10.1007/978-981-19-1142-2_10

Cited by 27 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…XAI provides explanations for AI-based decisions. This is important to the customers to convince of the AI-based decisions on credit evaluation [154].…”

Section: ) Explainable Ai(xai)-based Trust Establishmentmentioning

confidence: 99%

The Role of Blockchain in Finance Beyond Cryptocurrency: Trust, Data Management, and Automation

Chen,

Wei,

Wang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Blockchain has been a vibrant technology in the past decade, with a wide variety of applications across different industrial sectors. The concept of blockchain has been widely recognized as an enabler for cryptocurrency-based decentralized payments, with two major decentralized payment systems such as Bitcoin and Ethereum. However, the global acceptance of blockchain as a cryptocurrency sums up significant challenges that hinder the fast adaptation of cryptocurrency as a payment service enabler. In this survey, we explore the advantages of blockchain and its technical capabilities beyond cryptocurrency. We focus on the technical potential to ensure trust, data governance, and automation of the financial application domain utilizing the fundamental security features of blockchain, including consensus, digital signatures, and transparency. The significant subcomponents of trust, data management, and automation in banking and financial systems are also identified and discussed, including how blockchain and smart contracts can achieve the anticipated features of each subcomponent through their technical capabilities. In addition, we shed light on the position of blockchain-based applications in key application sectors of the banking and financing domain with a mapping of technical features with the application domains. Thereafter, the applicability of blockchain-based applications is evaluated with relevant regulatory definitions. Finally, we discuss open research challenges and potential future works with the blockchain in the domain of financial systems.

show abstract

“…XAI provides explanations for AI-based decisions. This is important to the customers to convince of the AI-based decisions on credit evaluation [154].…”

Section: ) Explainable Ai(xai)-based Trust Establishmentmentioning

confidence: 99%

The Role of Blockchain in Finance Beyond Cryptocurrency: Trust, Data Management, and Automation

Chen,

Wei,

Wang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…They performed experimentation on it using the KDD data set. Madhav and Tyagi 6 proposed XAI techniques for increasing trust in the domain of autonomous vehicles. They provided the insights and need for transparent AI solutions to increase trust in the sector.…”

Section: Related Workmentioning

confidence: 99%

“…How well domain experts and users can grasp and trust these models' functionality is one of the key factors that influence their successful adoption in cyber threat hunting. Stakeholders demand more transparency and explicability when these black‐box models are used to make significant predictions 6,7 . In cyber threat hunting, where specialists need significantly more information from the model than a simple binary outcome for their analysis, justifications supporting the output of AI models are essential.…”

Section: Introductionmentioning

confidence: 99%

“…Stakeholders demand more transparency and explicability when these black-box models are used to make significant predictions. 6,7 In cyber threat hunting, where specialists need significantly more information from the model than a simple binary outcome for their analysis, justifications supporting the output of AI models are essential. Recent methods have been developed with the goal of helping users to better understand the inner workings of the AI models and their outcomes.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Explainable artificial intelligence envisioned security mechanism for cyber threat hunting

Kumar

Wazid

Singh

et al. 2023

Security and Privacy

View full text Add to dashboard Cite

Cyber threat hunting proactively searches for cyber threats, which are undetected by the traditional defense mechanisms. It scans deep to identify malicious programs (ie, malware) that escape from detection. It is important because sophisticated cyber threats can bypass the cyber security mechanisms. The performance of the cyber threat hunting can be improved through artificial intelligence (AI), especially, explainable AI (XAI), which adds trust component to the cyber threat hunting process. Due to the inclusion of XAI, the security experts get the full explanations of the detected threats as the working of the detection model in XAI is known. Information, like, which one is a threat, how it has been detected, and why it has been detected, can be obtained very easily due to the inclusion of XAI in the cyber threat hunting. Therefore, an XAI‐envisioned mechanism for cyber threat hunting has been proposed (in short, XAISM‐CTH). The network and threat models of XAISM‐CTH are designed and discussed. The conducted security analysis proves the security of XAISM‐CTH against various potential attacks. XAISM‐CTH also performs better than the other existing schemes. At the end, a practical implementation of XAISM‐CTH has been provided to observe its impact on the performance of the system.

show abstract

“…By offering explanations for the classification of a vehicle’s behavior as anomalous, XAI empowers researchers to scrutinize the safety and security of autonomous systems. Additionally, establishing trust in these XAI methods for autonomous vehicles is imperative for human operators [ 17 ], considering the life-critical decisions made by these vehicles. Moreover, shedding light on potential shortcomings in existing XAI methods assists developers in identifying and addressing issues, such as understanding the factors that led to incorrect explanations by XAI methods, thereby pinpointing the causes of erroneous outcomes by XAI models [ 18 ].…”

Section: Introductionmentioning

confidence: 99%

On Evaluating Black-Box Explainable AI Methods for Enhancing Anomaly Detection in Autonomous Driving Systems

Nazat,

Arreche,

Abdallah

2024

Sensors

View full text Add to dashboard Cite

The recent advancements in autonomous driving come with the associated cybersecurity issue of compromising networks of autonomous vehicles (AVs), motivating the use of AI models for detecting anomalies on these networks. In this context, the usage of explainable AI (XAI) for explaining the behavior of these anomaly detection AI models is crucial. This work introduces a comprehensive framework to assess black-box XAI techniques for anomaly detection within AVs, facilitating the examination of both global and local XAI methods to elucidate the decisions made by XAI techniques that explain the behavior of AI models classifying anomalous AV behavior. By considering six evaluation metrics (descriptive accuracy, sparsity, stability, efficiency, robustness, and completeness), the framework evaluates two well-known black-box XAI techniques, SHAP and LIME, involving applying XAI techniques to identify primary features crucial for anomaly classification, followed by extensive experiments assessing SHAP and LIME across the six metrics using two prevalent autonomous driving datasets, VeReMi and Sensor. This study advances the deployment of black-box XAI methods for real-world anomaly detection in autonomous driving systems, contributing valuable insights into the strengths and limitations of current black-box XAI methods within this critical domain.

show abstract

Explainable Artificial Intelligence (XAI): Connecting Artificial Decision-Making and Human Trust in Autonomous Vehicles

Cited by 27 publications

References 24 publications

The Role of Blockchain in Finance Beyond Cryptocurrency: Trust, Data Management, and Automation

The Role of Blockchain in Finance Beyond Cryptocurrency: Trust, Data Management, and Automation

Explainable artificial intelligence envisioned security mechanism for cyber threat hunting

On Evaluating Black-Box Explainable AI Methods for Enhancing Anomaly Detection in Autonomous Driving Systems

Contact Info

Product

Resources

About