Skip to content
View abd84's full-sized avatar
💭
Pushing boundaries, merging possibilities
💭
Pushing boundaries, merging possibilities

Block or report abd84

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. CryoET-Protein-Complex-Annotation-Classification CryoET-Protein-Complex-Annotation-Classification Public

    This project processes electron tomography (ET) data to detect and segment biological particles like proteins and viruses. It uses Copick for particle detection and applies segmentation algorithms,…

    Jupyter Notebook

  2. DermaStratif-Multiclass-Lesion-Stratification-and-diagnosis DermaStratif-Multiclass-Lesion-Stratification-and-diagnosis Public

    DermaStratif classifies skin lesion images into 8 disease categories using EfficientNet-B0 with advanced fine-tuning techniques like Base Training, Adapter Fine-Tuning, and LoRA Fine-Tuning. The pr…

    Jupyter Notebook

  3. Upwork-Data-Analysis-and-Budget-Skills-Prediction- Upwork-Data-Analysis-and-Budget-Skills-Prediction- Public

    This project involves a comprehensive analysis of Upwork project data using Power BI to uncover actionable trends and insights, with a focus on predicting key project attributes such as budget, req…

    1

  4. Adversarial-ResNet-Resilience-Gradient-Perturbation-Fidelity-Analysis- Adversarial-ResNet-Resilience-Gradient-Perturbation-Fidelity-Analysis- Public

    This project explores generating adversarial examples and fine-tuning the ResNet18 model on the MNIST dataset using techniques like FGSM and PGD. The model achieved 97.91% accuracy on clean data bu…

    Jupyter Notebook

  5. Universal-Prompt-Injection-for-LLMs-Adversarial-Evasion-Response-Manipulation- Universal-Prompt-Injection-for-LLMs-Adversarial-Evasion-Response-Manipulation- Public

    This project demonstrates how prompt injection can manipulate language models (LLMs) like GPT to generate targeted responses, with a 100% success rate in influencing the model's output.

    Jupyter Notebook

  6. Voice-to-Text-Summarizer-via-Transfer-learning-and-Semantic-Representation Voice-to-Text-Summarizer-via-Transfer-learning-and-Semantic-Representation Public

    This project builds a Voice-to-Text Summarizer using Hubert and Wave2Vec for speech recognition, and BART and BERT for summarization. Hubert outperformed Wave2Vec with 90.26% accuracy. BART and BER…

    Jupyter Notebook