iamgroot42

A-LINK

Code for A-LINK and A2-LINK

awesome-distribution-inference

An awesome list of papers on distribution/property inference in machine learning

blackboxsok

Code for 'SoK: Pitfalls in Evaluating Black-Box Attacks' , SaTML 2024.

distribution_inference

Code for our paper 'Formalizing Distribution Inference Risks'

Hardening-Deep-Neural-Networks-via-Adversarial-Model-Cascades

Official code repository for our publication 'Hardening Deep Neural Networks via Adversarial Model Cascades'

mimir

Python package for measuring memorization in LLMs.

nelec

Repository for our submission to the SemEval EmoContext Competition

places365_keras

VGG16 trained on Places365 model in Keras

sasuma

A Telegram Bot to interact with servers without ssh

sauron

Code for 'One Neuron to Fool Them All'

iamgroot42/mimir

Python package for measuring memorization in LLMs.

iamgroot42/Hardening-Deep-Neural-Networks-via-Adversarial-Model-Cascades

Official code repository for our publication 'Hardening Deep Neural Networks via Adversarial Model Cascades'

iamgroot42/awesome-distribution-inference

An awesome list of papers on distribution/property inference in machine learning

iamgroot42/FormEstDistRisks

Code for our work 'Formalizing and Estimating Distribution Inference Risks'

iamgroot42/dissecting_dist_inf

Code for `Dissecting Distribution Inference'

iamgroot42/IR_assignments

Course assignments for CSE508 (IR) at IIITD

iamgroot42/awesome-ml-privacy-attacks

An awesome list of papers on privacy attacks against machine learning

iamgroot42/blackboxsok

Code for 'SoK: Pitfalls in Evaluating Black-Box Attacks' , SaTML 2024.

iamgroot42/iiitdalumni

IIITD Alumni Website

iamgroot42/causal-reading-group-23

Website for reading group on Causal Learning, UVA (Summer 2023)

iamgroot42/distribution-inference-risks

Distribution Inference Risks: Identifying and Mitigating Sources of Leakage

iamgroot42/espnet

End-to-End Speech Processing Toolkit

iamgroot42/Face-Auditor

Official implementation of "FACE-AUDITOR: Data Auditing in Facial Recognition Systems" (USENIX Security 2023)

iamgroot42/Fine-Tuning-Whisper-on-LibriSpeech

The code for fine-tuning OpenAI's Whisper model on the LibriSpeech dataset.

iamgroot42/iamgroot42

iamgroot42/inception-score-pytorch

Inception Score for GANs in Pytorch

iamgroot42/llm-attacks

Universal and Transferable Attacks on Aligned Language Models

iamgroot42/llmrisks.github.io

Website for UVA Seminar on Risks (and Benefits) of Generative AI and Large Language Models

iamgroot42/localizing-memorization

Official Repository for ICML 2023 paper "Can Neural Network Memorization Be Localized?"

iamgroot42/MIA_defense_HAMP

Code for the paper "Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction" in NDSS'24.

iamgroot42/MICO

Membership Inference Competition

iamgroot42/mimir.github.io

Project page for MIMIR

iamgroot42/ml_privacy_meter

Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.

iamgroot42/permutation_invariant_network

PyTorch implementation for Permutation Invariant Network

iamgroot42/personal-website

iamgroot42/secml_malware

Create adversarial attacks against machine learning Windows malware detectors

iamgroot42/SuperDeepFool

iamgroot42/tdc_23

My submission to TDC'23 challenge at NeurIPS

iamgroot42/torch-influence

A simple PyTorch implementation of influence functions.

iamgroot42/uvasrg.github.io

Website for UVA SRG