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.
A Bayesian Incentive Mechanism for Poison-Resilient Federated Learning
Multi-Trigger Poisoning Amplifies Backdoor Vulnerabilities in LLMs
Addressing The Devastating Effects Of Single-Task Data Poisoning In Exemplar-Free Continual Learning
Tuning without Peeking: Provable Privacy and Generalization Bounds for LLM Post-Training
Generalization under Byzantine & Poisoning Attacks: Tight Stability Bounds in Robust Distributed Learning
Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
Data Shifts Hurt CoT: A Theoretical Study
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols
Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
Securing Traffic Sign Recognition Systems in Autonomous Vehicles
VLMs Can Aggregate Scattered Training Patches
Cascading Adversarial Bias from Injection to Distillation in Language Models
Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems
Distributed Federated Learning for Vehicular Network Security: Anomaly Detection Benefits and Multi-Domain Attack Threats
Are Time-Series Foundation Models Deployment-Ready? A Systematic Study of Adversarial Robustness Across Domains
Security Concerns for Large Language Models: A Survey
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers
A Linear Approach to Data Poisoning
BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection
Sybil-based Virtual Data Poisoning Attacks in Federated Learning
Stealthy LLM-Driven Data Poisoning Attacks Against Embedding-Based Retrieval-Augmented Recommender Systems
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
Adversarial Robustness of Deep Learning Models for Inland Water Body Segmentation from SAR Images
What's Pulling the Strings? Evaluating Integrity and Attribution in AI Training and Inference through Concept Shift
A Geometric Approach to Problems in Optimization and Data Science
Investigating cybersecurity incidents using large language models in latest-generation wireless networks
ControlNET: A Firewall for RAG-based LLM System
Diversity-aware Dual-promotion Poisoning Attack on Sequential Recommendation
Sky of Unlearning (SoUL): Rewiring Federated Machine Unlearning via Selective Pruning
Clean Image May be Dangerous: Data Poisoning Attacks Against Deep Hashing
Data Poisoning in Deep Learning: A Survey
Optimizing ML Training with Metagradient Descent
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.