Datasets, clues and state-of-the-arts for multimedia forensics: An extensive review

A Yadav, DK Vishwakarma - Expert Systems with Applications, 2024 - Elsevier
With the large chunks of social media data being created daily and the parallel rise of
realistic multimedia tampering methods, detecting and localising tampering in images and …

[HTML][HTML] A hybrid approach for adversarial attack detection based on sentiment analysis model using Machine learning

R Amin, R Gantassi, N Ahmed, AH Alshehri… - … Science and Technology …, 2024 - Elsevier
One of the main subfields of Machine Learning (ML) that deals with human language for
intelligent applications is Natural Language Processing (NLP). One of the biggest problems …

Cross-domain facial expression recognition based on adversarial attack fine-tuning learning

Y Zhang, Z Sun - Engineering Applications of Artificial Intelligence, 2024 - Elsevier
Expression recognition is important in artificial intelligence research and has broad
application prospects in medical care and transportation. However, owing to differences in …

Inflect-text: a novel mechanism to evade neural text classifiers by leveraging word inflectional perturbations

A Bajaj, DK Vishwakarma - International Journal of Information Security, 2025 - Springer
Advanced neural text classifiers have shown remarkable ability in the task of classification.
The investigation illustrates that text classification models have an inherent vulnerability to …

Don't be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks

S Yu, J Choi, Y Kim - arxiv preprint arxiv:2403.15467, 2024 - arxiv.org
Offensive language detection is an important task for filtering out abusive expressions and
improving online user experiences. However, malicious users often attempt to avoid filtering …

Deceiving Deep Learning-based Fraud SMS Detection Models through Adversarial Attacks

A Bajaj, DK Vishwakarma - 2023 17th International Conference …, 2023 - ieeexplore.ieee.org
Short Messaging Service (SMS) is one of the most extensively utilized mobile applications
for communication around the world. Smishing is the technique of delivering harmful SMS to …

ARG-Net: Adversarial Robust Generalized Network to Defend Against Word-Level Textual Adversarial Attacks

A Bajaj, DK Vishwakarma - 2024 IEEE 9th International …, 2024 - ieeexplore.ieee.org
Natural Language Processing models have strong performance across various applications,
although they are susceptible to manipulation by adversarial instances. A minor disturbance …

BEACOMP: A Novel Textual Adversarial Attack Architecture for Unveiling the Fragility of Neural Text Classifiers

R Sharma, A Ghosh, A Bajaj… - 2024 2nd International …, 2024 - ieeexplore.ieee.org
Natural Language Processing models are now being used more than ever before and they
have been quite remarkable in applications like sentiment classification, text generation …

IRIS: Intelligent Responsive Interface Solution, a promising Desktop Assistant for Differently-Abled

A Karkra, R Singh… - 2024 2nd International …, 2024 - ieeexplore.ieee.org
In a quickly progressing digital world, the arrival of virtual assistants has become a
revolutionary principle for human-computer interactions. In this research project, an AI …

[PDF][PDF] REVOLUTIONIZING COTTON FARMING: CO-CNN INTEGRATION FOR DISEASE IDENTIFICATION AND YIELD PREDICTION

S GOVINDASAMY, D JAYARAJ - Journal of Theoretical and Applied …, 2024 - jatit.org
In agriculture, accurate identification of cotton plant diseases and prediction of yield are
crucial for ensuring crop health and optimizing production. This abstract explores the …