AI Secure

DecodingTrust

A Comprehensive Assessment of Trustworthiness in GPT Models

Certified-Robustness-SoK-Oldver

This repo keeps track of popular provable training and verification approaches towards robust neural networks, including leaderboards on popular datasets and paper categorization.

VeriGauge

A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]

InfoBERT

[ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective" by Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu

FLBenchmark-toolkit

Federated Learning Framework Benchmark (UniFed)

Robustness-Against-Backdoor-Attacks

RAB: Provable Robustness Against Backdoor Attacks

DataLens

[CCS 2021] "DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation" by Boxin Wang*, Fan Wu*, Yunhui Long*, Luka Rimanic, Ce Zhang, Bo Li

G-PATE

[NeurIPS 2021] "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators" by Yunhui Long*, Boxin Wang*, Zhuolin Yang, Bhavya Kailkhura, Aston Zhang, Carl A. Gunter, Bo Li

Transferability-Reduced-Smooth-Ensemble

semantic-randomized-smoothing

[CCS 2021] TSS: Transformation-specific smoothing for robustness certification

SemAttack

[NAACL 2022] "SemAttack: Natural Textual Attacks via Different Semantic Spaces" by Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li

aug-pe

Differentially Private Synthetic Data via Foundation Model APIs 2: Text

adversarial-glue

[NeurIPS 2021] "Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models" by Boxin Wang*, Chejian Xu*, Shuohang Wang, Zhe Gan, Yu Cheng, Jianfeng Gao, Ahmed Hassan Awadallah, Bo Li.

COPA

[ICLR 2022] COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

CROP

[ICLR 2022] CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

CoPur

CoPur: Certifiably Robust Collaborative Inference via Feature Purification (NeurIPS 2022)

DPFL-Robustness

[CCS 2023] Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks

Layerwise-Orthogonal-Training

Certified-Fairness

Code for Certifying Some Distributional Fairness with Subpopulation Decomposition [NeurIPS 2022]

SecretGen

A general model inversion attack against large pre-trained models.

TextGuard

TextGuard: Provable Defense against Backdoor Attacks on Text Classification

FedGame

Official implementation for paper "FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning" (NeurIPS 2023).

COPA_Atari

transferability-versus-robustness

COPA_Highway

DecodingTrust-Data-Legacy

DMLW2022

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

hf-blog

Public repo for HF blog posts

VFL-ADMM

Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM (SaTML 2024)