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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Data Poisoning Attacks on EEG Signal-based Risk Assessment Systems
Temporal Robustness against Data Poisoning
Run-Off Election: Improved Provable Defense against Data Poisoning Attacks
CATFL: Certificateless Authentication-based Trustworthy Federated Learning for 6G Semantic Communications
Face Recognition in the age of CLIP & Billion image datasets
Explainable Data Poison Attacks on Human Emotion Evaluation Systems based on EEG Signals
Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application
TrojanPuzzle: Covertly Poisoning Code-Suggestion Models
Silent Killer: A Stealthy, Clean-Label, Black-Box Backdoor Attack
Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
Defending Against Disinformation Attacks in Open-Domain Question Answering
Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning
Rethinking Backdoor Data Poisoning Attacks in the Context of Semi-Supervised Learning
Data Poisoning Attack Aiming the Vulnerability of Continual Learning
Backdoor Vulnerabilities in Normally Trained Deep Learning Models
Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners
Analysis and Detectability of Offline Data Poisoning Attacks on Linear Dynamical Systems
Backdoor Attacks for Remote Sensing Data with Wavelet Transform
CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
FLock: Defending Malicious Behaviors in Federated Learning with Blockchain
Try to Avoid Attacks: A Federated Data Sanitization Defense for Healthcare IoMT Systems
Generative Poisoning Using Random Discriminators
Amplifying Membership Exposure via Data Poisoning
FocusedCleaner: Sanitizing Poisoned Graphs for Robust GNN-based Node Classification
Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario
Training set cleansing of backdoor poisoning by self-supervised representation learning
Not All Poisons are Created Equal: Robust Training against Data Poisoning
How to Sift Out a Clean Data Subset in the Presence of Data Poisoning?
Detecting Backdoors in Deep Text Classifiers
On Optimal Learning Under Targeted Data Poisoning
Understanding Influence Functions and Datamodels via Harmonic Analysis
Data Poisoning Attacks Against Multimodal Encoders
Adversarial Robustness of Representation Learning for Knowledge Graphs
On the Robustness of Random Forest Against Untargeted Data Poisoning: An Ensemble-Based Approach
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.