Search Results - machine+learning

114 Results Sort By:
Exploiting Class Probabilities for Black-Box Sentence-Level Attacks
Background Text classification models have become increasingly prevalent in cybersecurity applications, but remain susceptible to adversarial examples (e.g., carefully crafted sentences with human-unrecognizable changes to the inputs, that are misclassified). Adversarial attacks provide profound insights into the classifiers’ vulnerabilities,...
Published: 8/21/2025   |   Inventor(s): Raha Moraffah, Huan Liu
Keywords(s): Machine Learning, Natural Language Processing, Red teaming, Security
Category(s): Physical Science, Applied Technologies, Artificial Intelligence/Machine Learning, Cybersecurity
Methods and Systems for Low-Cost Medical Image Annotation Using Non-experts (Case No. 2025-108)
Summary: UCLA researchers in the Department of Electrical and Computer Engineering have developed an AI-based interface designed to enable individuals without specialized training to identify arthritis in medical imaging. Background: The use of artificial intelligence (AI) for medical imaging analysis holds great promise for the future of healthcare....
Published: 7/23/2025   |   Inventor(s): Xiang Chen, Youngseung Jeon, Christopher Hwang
Keywords(s): 3D tissue imaging, AI-guided diagnostics, AI-guided medical imaging, AI-guided medical intervention, arthritis, Artifical Intelligence (Machine Learning, Data Mining), Artificial Intelligence, artificial intelligence algorithms, artificial intelligence augmentation, artificial intelligence/machine learning models, Artificial Neural Network, bioimaging, Computer-Aided Diagnosis, computer-aided radiology, Diagnostic Markers & Platforms, Diagnostic Test, diagnostics, generative artificial intelligence, Image Analysis, Image Resolution, Imaging, infrared thermal imaging, Machine Learning, machine learning modeling, machine perception, Magnetic Resonance Imaging Medical Physics, Magnetic Resonance Imaging Pathology, Medical artificial intelligence (AI), Medical diagnostics, Medical Imaging, Microscopy And Imaging, non-invasive imaging, osteoarthritis, radial MRI, radiologic imaging, Radiology, Radiology / Radiomitigation, radiosurgery
Category(s): Software & Algorithms, Software & Algorithms > AI Algorithms, Software & Algorithms > Artificial Intelligence & Machine Learning, Software & Algorithms > Digital Health, Software & Algorithms > Image Processing, Life Science Research Tools, Life Science Research Tools > Lab Equipment, Life Science Research Tools > Microscopy And Imaging, Medical Devices, Medical Devices > Medical Imaging, Medical Devices > Monitoring And Recording Systems, Therapeutics, Therapeutics > Musculoskeletal Disease, Therapeutics > Radiology
Subgraph Matching for High-Throughput DNA-Aptamer Secondary Structure Classification and Machine Learning Interpretability (Case No. 2025-104)
Intro Sentence: UCLA researchers in the Department of Mathematics have developed machine learning methods to rapidly identify novel aptamer sequences for target binding to accelerate highly-accurate diagnostic and therapeutic development. Background: Aptamers are single-stranded nucleotide polymers that bind with high affinity to targets such as...
Published: 8/19/2025   |   Inventor(s): Andrea Bertozzi, Anne Andrews, Matthew Tyler, Paolo Climaco, Noelle Mitchell
Keywords(s): Advanced Computing / AI, advanced computing methods, Aptamers, Artifical Intelligence (Machine Learning, Data Mining), artificial intelligence/machine learning models, bioinformatics pipeline, cancer target, clustering, computational efficiency, computational efficiency and analysis, design software, DNA clustering, DNA oligomer, DNA Sequencing, Drug, Drug Delivery, Drug Development, Drug Discovery, drug screening, high throughput, high throughput assays, high throughput testing, high-throughput analysis, High-Throughput Screening, interpretability, pipeline, large-scale parallelization, Machine Learning, machine learning modeling, motif structures, open source, open source code, OpenAI, Pharmaceutical Drug, protein classification, secondary structure, SELEX, sequences of interest, single strand DNA sequences, Software, Software & Algorithms, Software Development Tools, Software-enabled learning, subgraph matching, target binding, target detection, Targeted Therapy, Targets And Assays, tissue targeting accuracy
Category(s): Software & Algorithms, Software & Algorithms > AI Algorithms, Software & Algorithms > Artificial Intelligence & Machine Learning, Software & Algorithms > Data Analytics, Life Science Research Tools, Life Science Research Tools > Research Methods, Life Science Research Tools > Screening Libraries, Platforms, Platforms > Drug Delivery, Diagnostic Markers > Targets And Assays, Diagnostic Markers, Software & Algorithms > Bioinformatics
Adversarial Text Purification: Large Language Model Approach for Defense
Background Adversarial purification is a defense mechanism for safe-guarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques analyze and eliminate adversarial perturbations from the attacked inputs, and help to restore purified samples that retain similarity to the attacked...
Published: 6/27/2025   |   Inventor(s): Raha Moraffah, Shubh Khandelwal, Amrita Bhattacharjee, Huan Liu
Keywords(s): Artificial Intelligence, Defense Applications, Machine Learning, Natural Language Processing, Security, Text Mining
Category(s): Physical Science, Artificial Intelligence/Machine Learning, Applied Technologies, Cybersecurity
Methods and Systems for Detecting Disinformation Generated by Large Language Models
Background The rapid dissemination of news is an important factor for the global population to stay up to date with current events, or to make well-informed decisions in dynamic sectors like the stock market. Journalists typically include large amounts of quantitative information using data visualization to help enhance accessibility and comprehension...
Published: 6/17/2025   |   Inventor(s): Bohan Jiang, Zhen Tan, Ayushi Nirmal, Huan Liu
Keywords(s): Data Mining, Disinformation, Large Language Model, Machine Learning
Category(s): Cybersecurity, Physical Science, Artificial Intelligence/Machine Learning
Cellular User Localization System: SMS Side-Channel Timing Analysis Method and Apparatus
User localization through SMS serves as a low-cost, scalable alternative to conventional location tracking Background: User localization is traditionally achieved through GPS, network triangulation, or internet-assisted location sharing. GPS-based tracking depends on device permissions, while network-based methods require extensive infrastructure...
Published: 8/21/2025   |   Inventor(s): Evangelos Bitsikas, Theodor Schnitzler, Christina Pöpper, Aanjhan Ranganathan
Keywords(s): Cellular Networks, Communications, Cyber Security, Machine Learning, Mobile devices, Next-generation Mobile Networks, positioning systems
Category(s): Technology Classifications > 3. Computer Science > Network communications, Technology Classifications > 3. Computer Science > Cyber Security
Algorithm for Identifying Images of Fluorescently-Labeled Cells
Improves the ability to distinguish multiple fluorophores with overlapping emission spectra in biological images of labeled cells by a factor of two or more. Background: Cells (including normal and tumor cells), tissues, microbial communities, and other biological systems generally consist of multiple interacting components, especially proteins...
Published: 8/21/2025   |   Inventor(s): Alex Valm, Yunlong Feng
Keywords(s): bacterial cells, bacterial infection, bioengineering, biofilm control, bioinformatics, biomarker diagnostics, biomarkers, cancer, cell biology, computational biology, dental, diagnostics, digital image processing, fluorescence, fluorescence spectroscopy, gene expression analysis, image analysis, image processing, machine learning, medical imaging, microbial pathogenesis, personalized medicine, RNA, saliva, scanning microscopy, Technologies
Category(s): Campus > University at Albany, Technology Classifications > Biological Materials, Technology Classifications > Biomedical Science and Engineering, Technology Classifications > Healthcare, Technology Classifications > Medical Imaging, Technology Classifications > Research Tools and Reagents, Technology Classifications > Therapeutics and Vaccines
Automated Hidden Neuron Optimization for MLPs
Advantages: Maximizes accuracy with fewer neurons through automated, adaptive neural network tuning Reduces data size by over 80% using advanced hybrid feature selection Ensures scalable, overfitting-resistant models with cross-validation and early stopping built-in Summary: Determining the optimal number of hidden neurons in Multilayer Perceptrons...
Published: 7/9/2025   |   Inventor(s): Srinivas Katkoori, Susmitha Boyidapu, Lakshmi Kavya Kalyanam
Keywords(s): Artificial Intelligence, Datasets, Machine Learning
Category(s): Technology Classifications > Computer Science > Algorithms, Technology Classifications > Computer Science > Datasets
Modeling Flow of Resources in a Supply Chain
Supply chains provide a network describing how resources move from a source to delivery for consumption by the end user. Supply chains also involve the components involved in production and transportation of the commodities being moved in the supply chain. There is a need for modeling links in a supply chain to estimate supply and demand and to ensure...
Published: 4/16/2025   |   Inventor(s): Kevin Gurney, Deborah Huntzinger, Taha Moiz, Nathan Parker, Richard Rushforth, Benjamin Ruddell
Keywords(s): Algorithm Development, Machine Learning, Manufacturing, PS-Computing and Information Technology, PS-Manufacturing,Construction,Mechanical, Resource Management
Category(s): Artificial Intelligence/Machine Learning, Computing & Information Technology, Manufacturing/Construction/Mechanical, Physical Science
Unstructured Pruning for Multi-Layer Perceptrons with Tanh Activation
Advantages: Reduces neuron count by 72% (breast cancer) and 36.8% (MNIST) for efficiency Maintains high accuracy with only 5.25% average loss for MNIST dataset pruning Optimized for IoT and edge computing by reducing computational and memory needs Uses mean-based pruning for tanh activation to enhance model performance efficiently Summary: Modern...
Published: 1/30/2025   |   Inventor(s): Srinivas Katkoori, Lakshmi Kavya Kalyanam
Keywords(s): Machine Learning
Category(s): Technology Classifications > Computer Science > Network Systems, Technology Classifications > Data/AI > Cybersecurity - Data/AI
1 2 3 4 5 6 7 8 9 10 ...