Back
Papershelf
Paper summaries from courses taken in Vision and Language and Security for Deep Neural Networks and LLMs
- Understanding Technical Research Papers
New to research? A summary of my learnings on how to get the more out reading efficiently
- Hyper-Graphs & Visual Question Answering
A paper review summary part of my coursework in CSE597: Vision and Language
- Nets for Adversarial Attacks - GAN
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- AttriGuard
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- Prompt-based Attack on LLMs
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- Video-to-Image Affordance Grounding
A paper review summary part of my coursework in CSE597: Vision and Language
- Hiding data within NNs
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- Data Extraction from Model APIs
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- Data extractions from LLMs
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- Backdoor Attack Transferability
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- Neural Cleanse
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- Poisoning Encoders
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- CLIP & Multimodal Prompting
A paper review summary part of my coursework in CSE597: Vision and Language
- RanMASK against Text Adversarial Attacks
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- Bagging as a Defense
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning
- Shielding DL Models from Adversaries
A paper review summary part of my coursework in IST597: Trustworthy Machine Learning