AI Secure

UIUC Secure Learning Lab

University of Illinois at Urbana-Champaign

Pinned Repositories

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.
99 13 010
CRFL
CRFL: Certifiably Robust Federated Learning against Backdoor Attacks (ICML 2021)
Language:Python71 3 415
DBA
DBA: Distributed Backdoor Attacks against Federated Learning (ICLR 2020)
Language:Python177 2 1446
DecodingTrust
A Comprehensive Assessment of Trustworthiness in GPT Models
Language:Python263 6 2256
FLBenchmark-toolkit
Federated Learning Framework Benchmark (UniFed)
Language:Python47 3 55
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
Language:Python83 3 67
Meta-Nerual-Trojan-Detection
Language:Python62 3 112
multi-task-learning
Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxiang Wang, Han Zhao, Bo Li.
Language:Python67 2 09
SemanticAdv
Language:Python60 3 410
VeriGauge
A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]
Language:C88 6 47

AI Secure's Repositories

AI-secure/DecodingTrust
A Comprehensive Assessment of Trustworthiness in GPT Models
Language:Python263 6 2256
AI-secure/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.
99 13 010
AI-secure/VeriGauge
A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]
Language:C88 6 47
AI-secure/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
Language:Python83 3 67
AI-secure/FLBenchmark-toolkit
Federated Learning Framework Benchmark (UniFed)
Language:Python47 3 55
AI-secure/Robustness-Against-Backdoor-Attacks
RAB: Provable Robustness Against Backdoor Attacks
Language:Python39 5 25
AI-secure/aug-pe
[ICML 2024] Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Language:Python28 5 37
AI-secure/Transferability-Reduced-Smooth-Ensemble
Language:Python22 3 88
AI-secure/semantic-randomized-smoothing
[CCS 2021] TSS: Transformation-specific smoothing for robustness certification
Language:Roff21 3 13
AI-secure/SemAttack
[NAACL 2022] "SemAttack: Natural Textual Attacks via Different Semantic Spaces" by Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li
Language:Python19 2 75
AI-secure/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.
Language:Python9 1 01
AI-secure/CoPur
CoPur: Certifiably Robust Collaborative Inference via Feature Purification (NeurIPS 2022)
Language:Python9 1 01
AI-secure/CROP
[ICLR 2022] CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
Language:Python8 2 12
AI-secure/COPA
[ICLR 2022] COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks
7 2 01
AI-secure/MMDT
Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models
Language:Jupyter Notebook7 3 02
AI-secure/AdvWeb
Language:Jupyter Notebook6
AI-secure/DPFL-Robustness
[CCS 2023] Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks
Language:Python6 3 00
AI-secure/TextGuard
TextGuard: Provable Defense against Backdoor Attacks on Text Classification
Language:Python6 3 00
AI-secure/Certified-Fairness
[NeurIPS 2022] Code for Certifying Some Distributional Fairness with Subpopulation Decomposition
Language:Python5 3 00
AI-secure/FedGame
Official implementation for paper "FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning" (NeurIPS 2023).
Language:Python5 3 10
AI-secure/Layerwise-Orthogonal-Training
Language:Python5 3 00
AI-secure/SecretGen
A general model inversion attack against large pre-trained models.
Language:Python4 1 12
AI-secure/COPA_Atari
Language:Python1 2 01
AI-secure/DMLW2022
Language:HTML1 1 01
AI-secure/helm
Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).
Language:Python0 0 00
AI-secure/transferability-versus-robustness
Language:Python0 3 00
AI-secure/COPA_Highway
Language:Jupyter Notebook2 0
AI-secure/DecodingTrust-Data-Legacy
Language:Python2 0
AI-secure/hf-blog
Public repo for HF blog posts
Language:Jupyter Notebook0 0
AI-secure/VFL-ADMM
Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM (SaTML 2024)
Language:Python2 0