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.
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
SAFELOC: Overcoming Data Poisoning Attacks in Heterogeneous Federated Machine Learning for Indoor Localization
Learning from Convolution-based Unlearnable Datasets
Reclaiming "Open AI" -- AI Model Serving Can Be Open Access, Yet Monetizable and Loyal
Learning and Unlearning of Fabricated Knowledge in Language Models
Inverting Gradient Attacks Makes Powerful Data Poisoning
Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions
Regularized Robustly Reliable Learners and Instance Targeted Attacks
Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning
PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning
Fragile Giants: Understanding the Susceptibility of Models to Subpopulation Attacks
Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning
On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
Empirical Perturbation Analysis of Linear System Solvers from a Data Poisoning Perspective
Survey of Security and Data Attacks on Machine Unlearning In Financial and E-Commerce
Data Poisoning-based Backdoor Attack Framework against Supervised Learning Rules of Spiking Neural Networks
SHFL: Secure Hierarchical Federated Learning Framework for Edge Networks
UTrace: Poisoning Forensics for Private Collaborative Learning
Clean Label Attacks against SLU Systems
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.