11 results found Sort:

THUYimingLi
backdoor-learning-resources THUYimingLi
168
1.1k
mit
38
A list of backdoor learning resources
ai-security deep-learning backdoor-attacks backdoor-defense machine-learning backdoor-learning
Created 2020-06-13
734 commits to master branch, last one 5 months ago
penghui-yang
awesome-data-poisoning-and-backdoor-attacks penghui-yang
18
203
mit
3
A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them (no longer maintained)
awesome-list data-poisoning backdoor-attacks backdoor-defense machine-learning
Created 2023-03-15
43 commits to master branch, last one 5 months ago
zihao-ai
Awesome-Backdoor-in-Deep-Learning zihao-ai
14
189
gpl-3.0
10
A curated list of papers & resources on backdoor attacks and defenses in deep learning.
paper awesome backdoor deep-learning backdoor-attacks backdoor-defense
Created 2022-10-11
28 commits to main branch, last one 9 months ago
bboylyg
NAD bboylyg
13
119
unknown
2
This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://openreview.net/pdf?id=9l0K4OM-oXE) in PyTorch.
pytorch backdoor-attacks backdoor-defense deep-neural-networks erasing-backdoor-triggers
Created 2021-01-21
21 commits to main branch, last one 2 years ago
HalilDeniz
BackDoorSim HalilDeniz
14
99
mit
1
BackdoorSim: An Educational into Remote Administration Tools
backdoor backdoors ransomware backdoorsim server-client backdoorpython backdoor-attack python-backdoor backdoor-attacks backdoor-defense backdoors-created python-socket-server remote-administrative-tool
Created 2024-01-29
5 commits to main branch, last one 10 months ago
csdongxian
ANP_backdoor csdongxian
13
55
unknown
2
Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"
pytorch neurips-2021 deep-learning backdoor-attacks backdoor-defense
Created 2021-10-26
10 commits to main branch, last one 2 years ago
YiZeng623
I-BAU YiZeng623
13
51
mit
2
Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''
ai-security deep-learning backdoor-attacks backdoor-defense adversarial-attacks adversarial-machine-learning
Created 2021-10-07
17 commits to main branch, last one 2 years ago
mtuann
fedlearn-backdoor-attacks mtuann
2
50
unknown
1
Fast integration of backdoor attacks in machine learning and federated learning.
backdoor-attacks backdoor-defense federated-learning adversarial-attacks
Created 2023-10-15
32 commits to main branch, last one about a year ago
KaiyuanZh
FLIP KaiyuanZh
2
48
mit
3
[ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
python defense privacy pytorch backdoor security byzantine computer-vision backdoor-attacks backdoor-defense federated-learning distributed-computing
Created 2023-02-02
9 commits to main branch, last one 9 days ago
wssun
TiSE-CodeLM-Security wssun
2
39
mit
1
This repository provide the studies on the security of language models for code (CodeLMs).
ai4se lm4se lm4code security ai-security language-model backdoor-attacks backdoor-defense code-intelligence adversarial-attacks adversarial-defense
Created 2023-11-04
162 commits to main branch, last one 8 days ago
HanxunH
CognitiveDistillation HanxunH
2
31
mit
1
[ICLR2023] Distilling Cognitive Backdoor Patterns within an Image
iclr pytorch iclr2023 deep-learning backdoor-attacks backdoor-defense deep-neural-networks
Created 2023-01-23
19 commits to main branch, last one 2 months ago