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.
Progressive Poisoned Data Isolation for Training-time Backdoor Defense
TrojFSP: Trojan Insertion in Few-shot Prompt Tuning
FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge
Data and Model Poisoning Backdoor Attacks on Wireless Federated Learning, and the Defense Mechanisms: A Comprehensive Survey
Forcing Generative Models to Degenerate Ones: The Power of Data Poisoning Attacks
FedBayes: A Zero-Trust Federated Learning Aggregation to Defend Against Adversarial Attacks
Mendata: A Framework to Purify Manipulated Training Data
Privacy and Copyright Protection in Generative AI: A Lifecycle Perspective
IMMA: Immunizing text-to-image Models against Malicious Adaptation
Universal Backdoor Attacks
Trainwreck: A damaging adversarial attack on image classifiers
Security and Privacy Challenges in Deep Learning Models
Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems
BrainWash: A Poisoning Attack to Forget in Continual Learning
PACOL: Poisoning Attacks Against Continual Learners
RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
Reputation-Based Federated Learning Defense to Mitigate Threats in EEG Signal Classification
Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
PrivacyGAN: robust generative image privacy
Histopathological Image Classification and Vulnerability Analysis using Federated Learning
Transferable Availability Poisoning Attacks
Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
Towards Poisoning Fair Representations
Post-Training Overfitting Mitigation in DNN Classifiers
Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models
HINT: Healthy Influential-Noise based Training to Defend against Data Poisoning Attacks
CyberForce: A Federated Reinforcement Learning Framework for Malware Mitigation
Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks
Systematic Testing of the Data-Poisoning Robustness of KNN
Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy
Analyzing the vulnerabilities in SplitFed Learning: Assessing the robustness against Data Poisoning Attacks
What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?
FedDefender: Backdoor Attack Defense in Federated Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.