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.
FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learning
Do-AIQ: A Design-of-Experiment Approach to Quality Evaluation of AI Mislabel Detection Algorithm
Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition System
Neural network fragile watermarking with no model performance degradation
Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attacks
Lethal Dose Conjecture on Data Poisoning
Testing the Robustness of Learned Index Structures
Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications
Backdoor Attacks on Crowd Counting
Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis
Robustness Evaluation of Deep Unsupervised Learning Algorithms for Intrusion Detection Systems
Autoregressive Perturbations for Data Poisoning
Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning
BagFlip: A Certified Defense against Data Poisoning
SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learning
PoisonedEncoder: Poisoning the Unlabeled Pre-training Data in Contrastive Learning
Federated Multi-Armed Bandits Under Byzantine Attacks
VPN: Verification of Poisoning in Neural Networks
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
GFCL: A GRU-based Federated Continual Learning Framework against Data Poisoning Attacks in IoV
Federated Learning: Balancing the Thin Line Between Data Intelligence and Privacy
Indiscriminate Data Poisoning Attacks on Neural Networks
Breaking Fair Binary Classification with Optimal Flipping Attacks
Machine Learning Security against Data Poisoning: Are We There Yet?
Robustly-reliable learners under poisoning attacks
Targeted Data Poisoning Attack on News Recommendation System by Content Perturbation
Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning
Degree-Preserving Randomized Response for Graph Neural Networks under Local Differential Privacy
Poisoning Attacks and Defenses on Artificial Intelligence: A Survey
An Equivalence Between Data Poisoning and Byzantine Gradient Attacks
Collaborative Self Organizing Map with DeepNNs for Fake Task Prevention in Mobile Crowdsensing
Redactor: A Data-centric and Individualized Defense Against Inference Attacks
Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-start
BEAS: Blockchain Enabled Asynchronous & Secure Federated Machine Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.