Papers with Code 아카이브
Data Poisoning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Data Poisoning is an adversarial attack that tries to manipulate the training dataset in order to control the prediction behavior of a trained model such that the model will label malicious examples into a desired classes (e.g., labeling spam e-mails as safe).
Source: Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analytics
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/yifansun99/2d-oob-joint-valuation
공식 코드2D-OOB: Attributing Data Contribution Through Joint Valuation Framework
https://github.com/yinglunxu/reward_poisoning_attack_drl
공식 코드Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning
https://github.com/yueeeeeeee/recsys-extraction-attack
공식 코드Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
https://github.com/yuji-roh/fr-train
공식 코드FR-Train: A Mutual Information-Based Approach to Fair and Robust Training
https://github.com/yuyang0901/effective-poison-identification
공식 코드Not All Poisons are Created Equal: Robust Training against Data Poisoning
https://github.com/yuyang0901/epic
공식 코드Not All Poisons are Created Equal: Robust Training against Data Poisoning
https://github.com/zhengyjzoe/imma
공식 코드IMMA: Immunizing text-to-image Models against Malicious Adaptation
https://github.com/zhziszz/visual-stitching
공식 코드https://github.com/zqypku/mm_poison
공식 코드https://worksheets.codalab.org/worksheets/0xbdd35bdd83b14f6287b24c9418983617
공식 코드https://github.com/EleutherAI/radioactive-text
https://github.com/HanxunH/Detect-CLIP-Backdoor-Samples
https://github.com/LostOxygen/poison_froggo
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
https://github.com/MindCode-4/code-14/tree/main/IMM
IMMA: Immunizing text-to-image Models against Malicious Adaptation
https://github.com/Nathangitlab/Backdoor-Attacks-on-Crowd-Counting
https://github.com/OpenMined/PyDentity
A Distributed Trust Framework for Privacy-Preserving Machine Learning
https://github.com/Recognito-Vision/Android-FaceRecognition-FaceLivenessDetection
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
https://github.com/ZJZAC/Poison-Ink
https://github.com/bboylyg/abl
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks
https://github.com/bxz9200/ultraclean
Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning
https://github.com/ebagdasa/backdoors101
https://github.com/ebagdasa/mithridates
Machine Learning Security against Data Poisoning: Are We There Yet?
https://github.com/emergent-misalignment/emergent-misalignment
https://github.com/jsrdcht/SSL-Backdoor
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
https://github.com/jzhang538/corruptencoder
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
https://github.com/kohpangwei/data-poisoning-release
https://github.com/kubershahi/ashoka-secureml
https://github.com/liuzrcc/ImageShortcutSqueezing
https://github.com/lmunoz-gonzalez/Poisoning-Attacks-with-Back-gradient-Optimization
Detection of Adversarial Training Examples in Poisoning Attacks through Anomaly Detection
https://github.com/lyqcom/opensentimentanalysis
Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems
https://github.com/mattbev/6.867-final-project
https://github.com/nwpuhkp/DRL-Backdoor-Pong
TrojDRL: Trojan Attacks on Deep Reinforcement Learning Agents
https://github.com/pps-lab/fl-analysis
https://github.com/privacytrustlab/adversarial_bias
On Adversarial Bias and the Robustness of Fair Machine Learning
https://github.com/prolearner/hypertorch
Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.