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.
Context is the Key: Backdoor Attacks for In-Context Learning with Vision Transformers
Blockchain-based Federated Recommendation with Incentive Mechanism
BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models
Protecting against simultaneous data poisoning attacks
Accelerating the Surrogate Retraining for Poisoning Attacks against Recommender Systems
Unlearnable Examples Detection via Iterative Filtering
Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms
2D-OOB: Attributing Data Contribution Through Joint Valuation Framework
Data Poisoning in LLMs: Jailbreak-Tuning and Scaling Laws
Mitigating Malicious Attacks in Federated Learning via Confidence-aware Defense
Model Hijacking Attack in Federated Learning
Blockchain for Large Language Model Security and Safety: A Holistic Survey
Trading Devil Final: Backdoor attack via Stock market and Bayesian Optimization
Data Poisoning: An Overlooked Threat to Power Grid Resilience
Turning Generative Models Degenerate: The Power of Data Poisoning Attacks
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
Partner in Crime: Boosting Targeted Poisoning Attacks against Federated Learning
Robust Yet Efficient Conformal Prediction Sets
A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends
Advancements in Recommender Systems: A Comprehensive Analysis Based on Data, Algorithms, and Evaluation
Neuromimetic metaplasticity for adaptive continual learning
If You Don't Understand It, Don't Use It: Eliminating Trojans with Filters Between Layers
Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning
Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
On the Robustness of Graph Reduction Against GNN Backdoor
Machine Unlearning Fails to Remove Data Poisoning Attacks
BadSampler: Harnessing the Power of Catastrophic Forgetting to Poison Byzantine-robust Federated Learning
FullCert: Deterministic End-to-End Certification for Training and Inference of Neural Networks
Imperceptible Rhythm Backdoor Attacks: Exploring Rhythm Transformation for Embedding Undetectable Vulnerabilities on Speech Recognition
A Study of Backdoors in Instruction Fine-tuned Language Models
Generalization Bound and New Algorithm for Clean-Label Backdoor Attack
Exploring Vulnerabilities and Protections in Large Language Models: A Survey
Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.