Learning with noisy labels via self-supervised adversarial noisy masking
Collecting large-scale datasets is crucial for training deep models, annotating the data,
however, inevitably yields noisy labels, which poses challenges to deep learning algorithms …
however, inevitably yields noisy labels, which poses challenges to deep learning algorithms …
My face my choice: Privacy enhancing deepfakes for social media anonymization
Recently, productization of face recognition and identification algorithms have become the
most controversial topic about ethical AI. As new policies around digital identities are …
most controversial topic about ethical AI. As new policies around digital identities are …
Visual content privacy protection: A survey
Vision is the most important sense for people, and it is also one of the main ways of
cognition. As a result, people tend to utilize visual content to capture and share their life …
cognition. As a result, people tend to utilize visual content to capture and share their life …
Shake to leak: Fine-tuning diffusion models can amplify the generative privacy risk
While diffusion models have recently demonstrated remarkable progress in generating
realistic images, privacy risks also arise: published models or APIs could generate training …
realistic images, privacy risks also arise: published models or APIs could generate training …
Unsupervised text deidentification
Deidentification seeks to anonymize textual data prior to distribution. Automatic
deidentification primarily uses supervised named entity recognition from human-labeled …
deidentification primarily uses supervised named entity recognition from human-labeled …
Quantitative Measurement and Analysis of Powder Holdups in a Packed Bed in the Presence of Internal Blocks and Raceway
S Lakshminarasimha, FSD Bosco, VA Gadi… - … Materials Transactions B, 2023 - Springer
The lateral injection of air and pulverised coal in the lower regions of a blast furnace is
experimentally represented by the lateral inlet of gas–powder through a tuyere which …
experimentally represented by the lateral inlet of gas–powder through a tuyere which …
Enc2: Privacy-Preserving Inference for Tiny IoTs via Encoding and Encryption
Privacy-preserving machine learning (PPML) techniques have allowed remote and private
inference for resource-constrained internet-of-things (IoT) devices on the cloud. The main …
inference for resource-constrained internet-of-things (IoT) devices on the cloud. The main …
Enhancing privacy in computer vision applications: an emotion preserving approach to obfuscate faces
B Shahbaz Nejad, P Roch, M Handte… - … Symposium on Visual …, 2022 - Springer
Computer vision offers many techniques to facilitate the extraction of semantic information
from images. If the images include persons, preservation of privacy in computer vision …
from images. If the images include persons, preservation of privacy in computer vision …
Text classification technique for discovering country-based publications from international COVID-19 publications
Objective The significant increase in the number of COVID-19 publications, on the one hand,
and the strategic importance of this subject area for research and treatment systems in the …
and the strategic importance of this subject area for research and treatment systems in the …