Imagen de Portada

From Theory to Practice: Evaluating Data Poisoning Attacks and Defenses in In-Context Learning on Social Media Health Discourse

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jhuma, Rabeya Amin, Faisal, Mostafa Mohaimen Akand
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Computation and Language Cryptography and Security
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

VAGUEGAN: Stealthy Poisoning and Backdoor Attacks on Image Generative Pipelines
por: Faisal, Mostafa Mohaimen Akand, et al.
Publicado: (2025)

Comparative sentiment analysis of public perception: Monkeypox vs. COVID-19 behavioral insights
por: Faisal, Mostafa Mohaimen Akand, et al.
Publicado: (2025)

SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks
por: Paracha, Anum, et al.
Publicado: (2025)

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
por: Guo, Wenkai, et al.
Publicado: (2025)

SCOUT: A Defense Against Data Poisoning Attacks in Fine-Tuned Language Models
por: Afane, Mohamed, et al.
Publicado: (2025)

Can In-Context Reinforcement Learning Recover From Reward Poisoning Attacks?
por: Sasnauskas, Paulius, et al.
Publicado: (2025)

A Data-Driven Defense against Edge-case Model Poisoning Attacks on Federated Learning
por: Purohit, Kiran, et al.
Publicado: (2023)

Self-Evaluation as a Defense Against Adversarial Attacks on LLMs
por: Brown, Hannah, et al.
Publicado: (2024)

Learning to Poison Large Language Models for Downstream Manipulation
por: Zhou, Xiangyu, et al.
Publicado: (2024)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
por: Zeng, Yifan, et al.
Publicado: (2024)

SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
por: Zhang, Heyi, et al.
Publicado: (2025)

Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data
por: Baumgärtner, Tim, et al.
Publicado: (2024)

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval
por: Chen, Taiye, et al.
Publicado: (2025)

Poison with Style: A Practical Poisoning Attack on Code Large Language Models
por: Tran, Khang, et al.
Publicado: (2026)

Stealthy Poisoning Attacks Bypass Defenses in Regression Settings
por: Carnerero-Cano, Javier, et al.
Publicado: (2026)

Data Reconstruction Attacks and Defenses: A Systematic Evaluation
por: Liu, Sheng, et al.
Publicado: (2024)

Provable Watermarking for Data Poisoning Attacks
por: Zhu, Yifan, et al.
Publicado: (2025)

FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning
por: Han, Sungwon, et al.
Publicado: (2024)

Sybil-based Virtual Data Poisoning Attacks in Federated Learning
por: Zhu, Changxun, et al.
Publicado: (2025)

Poisoning Attacks and Defenses to Federated Unlearning
por: Wang, Wenbin, et al.
Publicado: (2025)

Indiscriminate Data Poisoning Attacks on Neural Networks
por: Lu, Yiwei, et al.
Publicado: (2022)

Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement
por: Kim, Heegyu, et al.
Publicado: (2024)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
por: Shao, Zedian, et al.
Publicado: (2024)

Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems
por: Thornton, Scott
Publicado: (2026)

GShield: Mitigating Poisoning Attacks in Federated Learning
por: M., Sameera K., et al.
Publicado: (2025)

Inverting Gradient Attacks Makes Powerful Data Poisoning
por: Bouaziz, Wassim, et al.
Publicado: (2024)

Devil's Hand: Data Poisoning Attacks to Locally Private Graph Learning Protocols
por: He, Longzhu, et al.
Publicado: (2025)

Formalizing and Benchmarking Prompt Injection Attacks and Defenses
por: Liu, Yupei, et al.
Publicado: (2023)

Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
por: Lobo, Elita, et al.
Publicado: (2024)

RLShield: Practical Multi-Agent RL for Financial Cyber Defense with Attack-Surface MDPs and Real-Time Response Orchestration
por: Nayak, Srikumar
Publicado: (2026)

Data-centric NLP Backdoor Defense from the Lens of Memorization
por: Wang, Zhenting, et al.
Publicado: (2024)

Indiscriminate Data Poisoning Attacks on Pre-trained Feature Extractors
por: Lu, Yiwei, et al.
Publicado: (2024)

Data Poisoning Attacks in Intelligent Transportation Systems: A Survey
por: Wang, Feilong, et al.
Publicado: (2024)

Poisoning Attacks to Local Differential Privacy Protocols for Trajectory Data
por: Hsu, I-Jung, et al.
Publicado: (2025)

Local Environment Poisoning Attacks on Federated Reinforcement Learning
por: Ma, Evelyn, et al.
Publicado: (2023)

Transferable Availability Poisoning Attacks
por: Liu, Yiyong, et al.
Publicado: (2023)

Synthetic Tabular Data: Methods, Attacks and Defenses
por: Cormode, Graham, et al.
Publicado: (2025)

P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs
por: Zhao, Shuai, et al.
Publicado: (2025)

Denial-of-Service Poisoning Attacks against Large Language Models
por: Gao, Kuofeng, et al.
Publicado: (2024)

Practical Poisoning Attacks against Retrieval-Augmented Generation
por: Zhang, Baolei, et al.
Publicado: (2025)