- San Francisco, CA, USA
- https://amanpriyanshu.github.io/
- in/aman-priyanshu
- @AmanPriyanshu6
Highlights
- Pro
I'm an AI Researcher at Cisco focusing on AI for Cybersecurity. With a Masters from CMU, my research explores vulnerabilities in foundation models, privacy-preserving ML, and LLM security. My work has led to invitations to join OpenAI's Red Teaming Network & Anthropic's Bug Bounty Program, and earned recognition through the AAAI Undergraduate Consortium Scholar award. Check out myWebsite!
- Breaching Privacy in Real-World Synthetic Data
- FRACTURED-SORRY-Bench: A new multi-shot jailbreak dataset
Research Enthusiast.
👨🎓 Studying Privacy Engineering at Carnegie Mellon University.
My Interests:Deep Learning and Privacy Enabled Machine Learning
PinnedLoading
- Deep-Belief-Networks-in-PyTorch
Deep-Belief-Networks-in-PyTorch PublicThe aim of this repository is to create RBMs, EBMs and DBNs in generalized manner, so as to allow modification and variation in model types.
- Federated-Recommendation-Neural-Collaborative-Filtering
Federated-Recommendation-Neural-Collaborative-Filtering PublicFederated Neural Collaborative Filtering (FedNCF). Neural Collaborative Filtering utilizes the flexibility, complexity, and non-linearity of Neural Network to build a recommender system. Aim to fed…
- DP-HyperparamTuning
DP-HyperparamTuning PublicDP-HyperparamTuning offers an array of tools for fast and easy hypertuning of various hyperparameters for the DP-SGD algorithm.
- AdaptKeyBERT
AdaptKeyBERT PublicForked fromMaartenGr/KeyBERT
AdaptKeyBERT: keyword/keyphrase extraction with zero-shot and few-shot semi-supervised domain adaptation
- FedPAQ-MNIST-implemenation
FedPAQ-MNIST-implemenation PublicAn implementation of FedPAQ using different experimental parameters. We will be looking at different variations of how, r(number of clients to be selected), t (local epochs) and s (Quantizer levels))
- GeneticPromptLab
GeneticPromptLab PublicGeneticPromptLab uses genetic algorithms for automated prompt engineering (for LLMs), enhancing quality and diversity through iterative selection, crossover, and mutation, while efficiently explori…
Python 19
If the problem persists, check theGitHub status page orcontact support.