AI-secure/Knowledge-Enhanced-Machine-Learning-Pipeline AI-secure/Knowledge-Enhanced-Machine-Learning-Pipeline

  • Stars
    star
    10
  • Rank 1,807,489 (Top 36 %)
  • Language
    Python
  • Created over 3 years ago
  • Updated over 3 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
AI-secure/Knowledge-Enhanced-Machine-Learning-Pipeline
github

AI-secure

Reviews

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

Repository Details

Repository for Knowledge Enhanced Machine Learning Pipeline (KEMLP)

More Repositories

1

DecodingTrust

A Comprehensive Assessment of Trustworthiness in GPT Models
Python
254
star
2

DBA

DBA: Distributed Backdoor Attacks against Federated Learning (ICLR 2020)
Python
173
star
3

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.
98
star
4

VeriGauge

A united toolbox for running major robustness verification approaches for DNNs. [S&P 2023]
C
85
star
5

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
Python
83
star
6

CRFL

CRFL: Certifiably Robust Federated Learning against Backdoor Attacks (ICML 2021)
Python
69
star
7

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.
Python
64
star
8

Meta-Nerual-Trojan-Detection

Python
57
star
9

SemanticAdv

Python
54
star
10

FLBenchmark-toolkit

Federated Learning Framework Benchmark (UniFed)
Python
47
star
11

Robustness-Against-Backdoor-Attacks

RAB: Provable Robustness Against Backdoor Attacks
Python
35
star
12

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
Python
35
star
13

QEBA

Code for CVPR2020 paper QEBA: Query-Efficient Boundary-Based Blackbox Attack
Python
30
star
14

Big-but-Invisible-Adversarial-Attack

This repo contains the code for CVPR submission "Big but Invisible Adversarial Attack"
Python
30
star
15

Shapley-Study

[CVPR 2021] Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
Python
30
star
16

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
Python
27
star
17

aug-pe

[ICML 2024] Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Python
27
star
18

T3

[EMNLP 2020] "T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack" by Boxin Wang, Hengzhi Pei, Boyuan Pan, Qian Chen, Shuohang Wang, Bo Li
Python
26
star
19

KNN-PVLDB

Official Repo for "Efficient task-specific data valuation for nearest neighbor algorithms"
Jupyter Notebook
25
star
20

Transferability-Reduced-Smooth-Ensemble

Python
22
star
21

GMI-Attack

Python
21
star
22

semantic-randomized-smoothing

[CCS 2021] TSS: Transformation-specific smoothing for robustness certification
Roff
20
star
23

LinkTeller

[IEEE S&P 22] "LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis" by Fan Wu, Yunhui Long, Ce Zhang, Bo Li
Python
19
star
24

SemAttack

[NAACL 2022] "SemAttack: Natural Textual Attacks via Different Semantic Spaces" by Boxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li
Python
18
star
25

Uncovering-the-Connections-BetweenAdversarial-Transferability-and-Knowledge-Transferability

code for ICML 2021 paper in which we explore the relationship between adversarial transferability and knowledge transferability.
Python
16
star
26

Characterizing-Audio-Adversarial-Examples-using-Temporal-Dependency

ICLR 2019 Paper, "Characterizing Audio Adversarial Examples using Temporal Dependency".
Python
11
star
27

Does-Adversairal-Transferability-Indicate-Knowledge-Transferability

code for ICML 2021 paper in which we explore the relationship between adversarial transferability and knowledge transferability.
Python
11
star
28

stAdv-Spatially-Transformed-Adversarial-Examples-

Official Implementation of paper https://arxiv.org/abs/1801.02612
Python
10
star
29

CoPur

CoPur: Certifiably Robust Collaborative Inference via Feature Purification (NeurIPS 2022)
Python
9
star
30

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.
Python
9
star
31

NonLinear-BA

The code accompanying paper: Nonlinear Gradient Estimation for Query Efficient Blackbox Attack
Python
9
star
32

CROP

[ICLR 2022] CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing
Python
8
star
33

COPA

[ICLR 2022] COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks
8
star
34

PSBA

[ICML 2021] "Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation" by Jiawei Zhang*, Linyi Li*, Huichen Li, Xiaolu Zhang, Shuang Yang, Bo Li
Python
6
star
35

DPFL-Robustness

[CCS 2023] Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks
Python
6
star
36

Layerwise-Orthogonal-Training

Python
5
star
37

SecretGen

A general model inversion attack against large pre-trained models.
Python
4
star
38

Certified-Fairness

Code for Certifying Some Distributional Fairness with Subpopulation Decomposition [NeurIPS 2022]
Python
4
star
39

Meta-Neural-Kernel

The official implementation of Meta Neural Kernel (MNK), a kernel method for meta-learning
Python
4
star
40

TextGuard

TextGuard: Provable Defense against Backdoor Attacks on Text Classification
Python
4
star
41

KNN-shapley

Python
3
star
42

MMDT

Comprehensive Assessment of Trustworthiness in Multimodal Foundation Models
Jupyter Notebook
3
star
43

FedGame

Official implementation for paper "FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning" (NeurIPS 2023).
2
star
44

COPA_Atari

Python
1
star