Results 61 to 70 of about 7,756 (262)

Evaluating Pretrained Deep Learning Models for Image Classification Against Individual and Ensemble Adversarial Attacks

IEEE Access
The robustness of Deep Neural Networks (DNNs) against adversarial attacks is an important topic in the area of deep learning. To fully investigate the robustness of DNNs, this study examines four frequently used white box adversarial attack techniques ...
Mafizur Rahman, Prosenjit Roy, Sherri S. Frizell, Lijun Qian   +3 more
doaj   +1 more source

A Robust Method to Protect Text Classification Models against Adversarial Attacks

Proceedings of the International Florida Artificial Intelligence Research Society Conference, 2022
Text classification is one of the main tasks in natural language processing. Recently, adversarial attacks have shown a substantial negative impact on neural network-based text classification models. There are few defenses to strengthen model predictions
BALA MALLIKARJUNARAO GARLAPATI, Ajeet Kumar Singh, Srinivasa Rao Chalamala   +2 more
doaj   +1 more source

Playing in the Dark: Invisible Chess as a Laboratory for Strategic AI

AI &Innovation, EarlyView.
This paper shows that strategic AI evaluated on perfect‐information benchmarks can be brittle in real adversarial settings. By using invisible chess as a benchmark for hidden state and deception, it argues for stricter testing, human oversight, and more cautious governance of high‐stakes AI systems.
Paolo Ciancarini
wiley   +1 more source

A new method for countering evasion adversarial attacks on information systems based on artificial intelligence

Научно-технический вестник информационных технологий, механики и оптики
Modern artificial intelligence (AI) technologies are being used in a variety of fields, from science to everyday life. However, the widespread use of AI-based systems has highlighted a problem with their vulnerability to adversarial attacks.
A. A. Vorobeva, M. A. Matuzko, D. I. Sivkov, R. I. Safiullin, A. A. Menshchikov   +4 more
doaj   +1 more source

Adversarial attacks on an oblivious recommender [PDF]

Proceedings of the 13th ACM Conference on Recommender Systems, 2019
Can machine learning models be easily fooled? Despite the recent surge of interest in learned adversarial attacks in other domains, in the context of recommendation systems this question has mainly been answered using hand-engineered fake user profiles. This paper attempts to reduce this gap.
Konstantina Christakopoulou, Arindam Banerjee 0001   +1 more
openaire   +1 more source

Multi-concept adversarial attacks

CoRR, 2021
As machine learning (ML) techniques are being increasingly used in many applications, their vulnerability to adversarial attacks becomes well-known. Test time attacks, usually launched by adding adversarial noise to test instances, have been shown effective against the deployed ML models.
Vibha Belavadi, Yan Zhou 0001, Murat Kantarcioglu, Bhavani M. Thuraisingham   +3 more
openaire   +2 more sources

Artificial intelligence in enzyme catalysis: Emerging trends and applications in biocatalyst engineering

The Canadian Journal of Chemical Engineering, EarlyView.
Schematic representation of artificial intelligence approaches in enzyme catalysis, integrating bibliometric analysis, emerging research trends, and machine learning tools for enzyme design, prediction, and industrial biocatalytic applications. Abstract This study systematically explores the applications of artificial intelligence (AI) in enzyme ...
Misael Bessa Sales, Francisco Izaias da Silva Aires, Paulo Gonçalves de Sousa Junior, Calebe Da Rocha Silva, Emanuel Lino Rodrigues, Maria Cristiane Martins de Souza, José C. S. dos Santos   +6 more
wiley   +1 more source

Approximating High-Order Adversarial Attacks Using Runge−Kutta Methods

Tsinghua Science and Technology
Adversarial attacks craft adversarial examples (AEs) to fool convolution neural networks. The mainstream gradient-based attacks, based on first-order optimization methods, encounter bottlenecks to generate high transferable AEs attacking unknown models ...
Anjie Peng, Guoqiang Shi, Zhi Lin, Hui Zeng, Xing Yang   +4 more
doaj   +1 more source

Link Prediction Adversarial Attack

CoRR, 2018
Deep neural network has shown remarkable performance in solving computer vision and some graph evolved tasks, such as node classification and link prediction. However, the vulnerability of deep model has also been revealed by carefully designed adversarial examples generated by various adversarial attack methods.
Jinyin Chen, Ziqiang Shi, Yangyang Wu, Xuanheng Xu, Haibin Zheng   +4 more
openaire   +2 more sources

A Review of Artificial Intelligence in Ophthalmology: Key Aspects, Challenges, and Future Directions

Eye &ENT Research, EarlyView.
ABSTRACT Artificial intelligence (AI) is increasingly reshaping ophthalmology because the specialty depends heavily on structured imaging, quantitative measurements, and repeatable diagnostic workflows. This review provides a clinically grounded and translationally oriented synthesis of AI in ophthalmology, covering methodological foundations ...
Partha Pratim Ray
wiley   +1 more source