AI Secure

DecodingTrust

A Comprehensive Assessment of Trustworthiness in GPT Models

AgentPoison

[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning"

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

RedCode

[NeurIPS'24] RedCode: Risky Code Execution and Generation Benchmark for Code Agents

FLBenchmark-toolkit

Federated Learning Framework Benchmark (UniFed)

aug-pe

[ICML 2024 Spotlight] Differentially Private Synthetic Data via Foundation Model APIs 2: Text

Robustness-Against-Backdoor-Attacks

RAB: Provable Robustness Against Backdoor Attacks

semantic-randomized-smoothing

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

MMDT

Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models

UDora

[ICML 2025] UDora: A Unified Red Teaming Framework against LLM Agents

AdvAgent

FedGame

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

PolyGuard

TextGuard

TextGuard: Provable Defense against Backdoor Attacks on Text Classification

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.

SafeAuto

[ICML 2025] SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Models

CoPur

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

CROP

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

DPFL-Robustness

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

Layerwise-Orthogonal-Training

Certified-Fairness

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

SecretGen

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

VFL-ADMM

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

DMLW2022

helm

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

transferability-versus-robustness

DecodingTrust-Data-Legacy

hf-blog

Public repo for HF blog posts