Princeton INSPIRE Research Group

adv-patch-paper-list

A paper list for localized adversarial patch research

advml-traffic-sign

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

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).

membership-inference-evaluation

Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models

ModelPoisoning

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

PatchCleanser

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

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

proxy-distributions

[ICLR 2022 official code] Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?

SSD

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

inspire-group/ModelPoisoning

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

inspire-group/adv-patch-paper-list

A paper list for localized adversarial patch research

inspire-group/membership-inference-evaluation

Systematic Evaluation of Membership Inference Privacy Risks of Machine Learning Models

inspire-group/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).

inspire-group/PatchGuard

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

inspire-group/PatchCleanser

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

inspire-group/patch-defense-leaderboard

A Leaderboard for Certifiable Robustness against Adversarial Patch Attacks

inspire-group/unlearning-verification

verifying machine unlearning by backdooring

inspire-group/MIAdefenseSELENA

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

inspire-group/DetectorGuard

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

inspire-group/DP-RandP

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

inspire-group/ObjectSeeker

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

inspire-group/tta_risk

inspire-group/variation-regularization

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

inspire-group/RobustRAG

inspire-group/Rotation_BD

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

inspire-group/PatchCURE

inspire-group/LabelDP

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

inspire-group/quicstep

inspire-group/routing-aware-dns

A program to resolve DNS based on BGP route age.

inspire-group/multiclass_robust_lb

inspire-group/pki-resilience-processing

Code to copute the resilience of TLS domains. See resilience-computation/README.md for more.

inspire-group/pki-topology-simulator

Topology simulations based on modeling on quicksand for Internet topology simulations related to the PKI.

inspire-group/dns-lookup-data

Full-graph DNS lookup data collected from domains in Let's Encrypt logs.

inspire-group/log-loss-lower-bounds

inspire-group/multirobustbench

inspire-group/multirobustbench.github.io

inspire-group/open-mpic

Open Multi Perspective Issuance Corroboration Project

inspire-group/PAF_AT

Repository for DLS paper "Parameterizing activation functions for adversarial robustness"

inspire-group/robustbench

RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]