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.
Targeted Data Poisoning for Black-Box Audio Datasets Ownership Verification
Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data
Data Poisoning Attacks to Locally Differentially Private Range Query Protocols
Approaching the Harm of Gradient Attacks While Only Flipping Labels
No, of course I can! Refusal Mechanisms Can Be Exploited Using Harmless Fine-Tuning Data
Atlas: A Framework for ML Lifecycle Provenance & Transparency
FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in FL
Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning
Swallowing the Poison Pills: Insights from Vulnerability Disparity Among LLMs
Multi-Faceted Studies on Data Poisoning can Advance LLM Development
A Robust Attack: Displacement Backdoor Attack
DROP: Poison Dilution via Knowledge Distillation for Federated Learning
Filter, Obstruct and Dilute: Defending Against Backdoor Attacks on Semi-Supervised Learning
Detection of Physiological Data Tampering Attacks with Quantum Machine Learning
SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
TrojanTime: Backdoor Attacks on Time Series Classification
Safety at Scale: A Comprehensive Survey of Large Model Safety
Provably effective detection of effective data poisoning attacks
Poison-RAG: Adversarial Data Poisoning Attacks on Retrieval-Augmented Generation in Recommender Systems
A Novel Pearson Correlation-Based Merging Algorithm for Robust Distributed Machine Learning with Heterogeneous Data
Cut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution
Attacks on the neural network and defense methods
Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning
From Vulnerabilities to Remediation: A Systematic Literature Review of LLMs in Code Security
One Pixel is All I Need
BiCert: A Bilinear Mixed Integer Programming Formulation for Precise Certified Bounds Against Data Poisoning Attacks
Deep Learning Model Security: Threats and Defenses
Learning to Forget using Hypernetworks
Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models
Adversarial Data Poisoning Attacks on Quantum Machine Learning in the NISQ Era
Delta-Influence: Unlearning Poisons via Influence Functions
Reliable Poisoned Sample Detection against Backdoor Attacks Enhanced by Sharpness Aware Minimization
BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.