Adversarial attacks and defenses in explainable artificial intelligence: A survey

H Baniecki, P Biecek - Information Fusion, 2024 - Elsevier
Explainable artificial intelligence (XAI) methods are portrayed as a remedy for debugging
and trusting statistical and deep learning models, as well as interpreting their predictions …

[HTML][HTML] Talking human face generation: A survey

M Toshpulatov, W Lee, S Lee - Expert Systems with Applications, 2023 - Elsevier
Talking human face generation aims at synthesizing a natural human face that talks in
correspondence to the given text or audio series. Implementing the recently developed …

Graph neural networks: foundation, frontiers and applications

L Wu, P Cui, J Pei, L Zhao, X Guo - … of the 28th ACM SIGKDD conference …, 2022 - dl.acm.org
The field of graph neural networks (GNNs) has seen rapid and incredible strides over the
recent years. Graph neural networks, also known as deep learning on graphs, graph …

[HTML][HTML] Information fusion as an integrative cross-cutting enabler to achieve robust, explainable, and trustworthy medical artificial intelligence

A Holzinger, M Dehmer, F Emmert-Streib, R Cucchiara… - Information …, 2022 - Elsevier
Medical artificial intelligence (AI) systems have been remarkably successful, even
outperforming human performance at certain tasks. There is no doubt that AI is important to …

Sociotechnical envelopment of artificial intelligence: An approach to organizational deployment of inscrutable artificial intelligence systems

A Asatiani, P Malo, PR Nagbøl, E Penttinen… - Journal of the …, 2021 - research.aalto.fi
The paper presents an approach for implementing inscrutable (ie, nonexplainable) artificial
intelligence (AI) such as neural networks in an accountable and safe manner in …

[HTML][HTML] Adversarial attack and defence through adversarial training and feature fusion for diabetic retinopathy recognition

S Lal, SU Rehman, JH Shah, T Meraj, HT Rauf… - Sensors, 2021 - mdpi.com
Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the
security and robustness of the deployed algorithms need to be guaranteed. The security …

Usable XAI: 10 strategies towards exploiting explainability in the LLM era

X Wu, H Zhao, Y Zhu, Y Shi, F Yang, T Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
Explainable AI (XAI) refers to techniques that provide human-understandable insights into
the workings of AI models. Recently, the focus of XAI is being extended towards Large …

Black-box backdoor defense via zero-shot image purification

Y Shi, M Du, X Wu, Z Guan, J Sun… - Advances in Neural …, 2023 - proceedings.neurips.cc
Backdoor attacks inject poisoned samples into the training data, resulting in the
misclassification of the poisoned input during a model's deployment. Defending against …

Adversarial Attacks in Machine Learning: Key Insights and Defense Approaches

YL Khaleel, MA Habeeb… - Applied Data Science and …, 2024 - mesopotamian.press
There is a considerable threat present in genres such as machine learning due to
adversarial attacks which include purposely feeding the system with data that will alter the …

Deep learning for nano-photonic materials–the solution to everything!?

PR Wiecha - Current Opinion in Solid State and Materials Science, 2024 - Elsevier
Deep learning is currently being hyped as an almost magical tool for solving all kinds of
difficult problems that computers have not been able to solve in the past. Particularly in the …