inspire-group/unlearning-verification

Stars
17
Rank 1,257,181 (Top 25 %)
Language
Python
Created over 4 years ago
Updated over 1 year ago

inspire-group/unlearning-verification

inspire-group

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

verifying machine unlearning by backdooring

ModelPoisoning

Code for "Analyzing Federated Learning through an Adversarial Lens" https://arxiv.org/abs/1811.12470

SSD

SSD: A Unified Framework for Self-Supervised Outlier Detection [ICLR 2021]

adv-patch-paper-list

A paper list for localized adversarial patch research

membership-inference-evaluation

Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models

hydra

Code and checkpoints of compressed networks for the paper titled "HYDRA: Pruning Adversarially Robust Neural Networks" (NeurIPS 2020) (https://arxiv.org/abs/2002.10509).

PatchGuard

Code for paper "PatchGuard: A Provably Robust Defense against Adversarial Patches via Small Receptive Fields and Masking"

privacy-vs-robustness

Privacy Risks of Securing Machine Learning Models against Adversarial Examples

advml-traffic-sign

Code for the 'DARTS: Deceiving Autonomous Cars with Toxic Signs' paper

Jupyter Notebook

PatchCleanser

Code for "PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier"

patch-defense-leaderboard

A Leaderboard for Certifiable Robustness against Adversarial Patch Attacks

MVG-Mechansim

A module for the Matrix-Variate Gaussian (MVG) mechanism for differential privacy under matrix-valued query.

DetectorGuard

Code for "DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks"

MIAdefenseSELENA

[USENIX Security 2022] Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture

robustness-via-transport

OOD-Attacks

Attacks using out-of-distribution adversarial examples

DP-RandP

[NeurIPS 2023] Differentially Private Image Classification by Learning Priors from Random Processes

tta_risk

ObjectSeeker

Code for "ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking"

variation-regularization

Official code for the paper "Formulating Robustness Against Unforeseen Attacks"

Jupyter Notebook

robust_representation_similarity

Understanding robust learning through the lens of representation similarity

RON-Gauss

Implementation for the RON-Gauss system for non-interactive differentially-private data release.

Rotation_BD

Code for "Just Rotate it: Deploying Backdoor Attacks via Rotation Transformation"

sybilfuse

comps

exploring intentional connection migration for privacy

SICO-tools

Code for several of the tools used in the AMC CCS Paper "SICO: Surgical Interception Attacks by Manipulating BGP Communities"

Root-ORAM

PatchCURE

certificate-database

This is a MySQL dump backup of a database of 1.8 million certificates and corresponding BGP data from when those certificates were issued.

RobustRAG

proxy-distributions

Official repository for our paper titled "Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?"

advml_website

CA-vantage-point-selection

An algorithm designed to select best vantage points for use by CAs.

Counter-Raptor-Tor-Client

PinMe

This is the repo for the project, known as PinMe, http://arsalanmosenia.com/papers/Pinme_preprint.pdf

routing-aware-dns

A program to resolve DNS based on BGP route age.

BGP-age-false-positive-study

This repository is designed to compute the false positives of various age-based BGP monitoring systems for use by certificate authorities.

quicstep

LinkMirage

LabelDP

[PETS 2022] Machine Learning with Differentially Private Labels: Mechanisms and Frameworks