Search Results for author: Asif Salekin

Found 9 papers, 2 papers with code

Only My Model On My Data: A Privacy Preserving Approach Protecting one Model and Deceiving Unauthorized Black-Box Models

no code implementations14 Feb 2024 Weiheng Chai, Brian Testa, Huantao Ren, Asif Salekin, Senem Velipasalar

The datasets employed are ImageNet, for image classification, Celeba-HQ dataset, for identity classification, and AffectNet, for emotion classification.

Adversarial Attack Emotion Classification +4

Classifying Rhoticity of /r/ in Speech Sound Disorder using Age-and-Sex Normalized Formants

no code implementations25 May 2023 Nina R Benway, Jonathan L Preston, Asif Salekin, Yi Xiao, Harshit Sharma, Tara McAllister

Mispronunciation detection tools could increase treatment access for speech sound disorders impacting, e. g., /r/.

Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning

no code implementations17 Nov 2022 Brian Testa, Yi Xiao, Harshit Sharma, Avery Gump, Asif Salekin

Smart speaker voice assistants (VAs) such as Amazon Echo and Google Home have been widely adopted due to their seamless integration with smart home devices and the Internet of Things (IoT) technologies.

Speech Emotion Recognition

VeriCompress: A Tool to Streamline the Synthesis of Verified Robust Compressed Neural Networks from Scratch

no code implementations17 Nov 2022 Sawinder Kaur, Yi Xiao, Asif Salekin

This study introduces VeriCompress, a tool that automates the search and training of compressed models with robustness guarantees.

Pedestrian Detection

Deadwooding: Robust Global Pruning for Deep Neural Networks

no code implementations10 Feb 2022 Sawinder Kaur, Ferdinando Fioretto, Asif Salekin

The ability of Deep Neural Networks to approximate highly complex functions is key to their success.

Adversarial Robustness

Hyperspectral Image Super-Resolution in Arbitrary Input-Output Band Settings

no code implementations19 Mar 2021 Zhongyang Zhang, Zhiyang Xu, Zia Ahmed, Asif Salekin, Tauhidur Rahman

However, one of the fundamental limitations of these approaches is that they are highly dependent on image and camera settings and can only learn to map an input HSI with one specific setting to an output HSI with another.

Hyperspectral Image Super-Resolution Image Super-Resolution +1

Cannot find the paper you are looking for? You can Submit a new open access paper.