Buchumschlag

Defending Against Beta Poisoning Attacks in Machine Learning Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Gulciftci, Nilufer, Gursoy, M. Emre
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Cryptography and Security Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Injecting Bias into Text Classification Models using Backdoor Attacks
von: Yavuz, A. Dilara, et al.
Veröffentlicht: (2024)

Win-k: Improved Membership Inference Attacks on Small Language Models
von: Arkhmammadova, Roya, et al.
Veröffentlicht: (2025)

Defending Against Poisoning Attacks in Federated Learning with Blockchain
von: Dong, Nanqing, et al.
Veröffentlicht: (2023)

Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
von: Zhao, Shuai, et al.
Veröffentlicht: (2024)

No Free Lunch for Defending Against Prefilling Attack by In-Context Learning
von: Xue, Zhiyu, et al.
Veröffentlicht: (2024)

Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
von: Kirci, Onur Alp, et al.
Veröffentlicht: (2025)

Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks
von: Halloran, John T., et al.
Veröffentlicht: (2026)

FIDELIS: Blockchain-Enabled Protection Against Poisoning Attacks in Federated Learning
von: Carney, Jane, et al.
Veröffentlicht: (2025)

Optimal Defenses Against Gradient Reconstruction Attacks
von: Chen, Yuxiao, et al.
Veröffentlicht: (2024)

Unraveling the Connections between Privacy and Certified Robustness in Federated Learning Against Poisoning Attacks
von: Xie, Chulin, et al.
Veröffentlicht: (2022)

Uncovering and Aligning Anomalous Attention Heads to Defend Against NLP Backdoor Attacks
von: Jin, Haotian, et al.
Veröffentlicht: (2025)

Robustness Analysis of Machine Learning Models for IoT Intrusion Detection Under Data Poisoning Attacks
von: Wulnye, Fortunatus Aabangbio, et al.
Veröffentlicht: (2026)

Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
von: Liu, Fan, et al.
Veröffentlicht: (2024)

Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
von: Xu, Yuancheng, et al.
Veröffentlicht: (2024)

FedCC: Robust Federated Learning against Model Poisoning Attacks
von: Jeong, Hyejun, et al.
Veröffentlicht: (2022)

Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion
von: Zhu, Hongyu, et al.
Veröffentlicht: (2024)

Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
von: Yu, Zhe, et al.
Veröffentlicht: (2026)

Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents
von: Xu, Wenpeng
Veröffentlicht: (2026)

Defending Large Language Models Against Jailbreak Exploits with Responsible AI Considerations
von: Wong, Ryan, et al.
Veröffentlicht: (2025)

Prefix Guidance: A Steering Wheel for Large Language Models to Defend Against Jailbreak Attacks
von: Zhao, Jiawei, et al.
Veröffentlicht: (2024)

Have You Poisoned My Data? Defending Neural Networks against Data Poisoning
von: De Gaspari, Fabio, et al.
Veröffentlicht: (2024)

To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack
von: Zhuo, Terry Yue, et al.
Veröffentlicht: (2026)

Turning Generative Models Degenerate: The Power of Data Poisoning Attacks
von: Jiang, Shuli, et al.
Veröffentlicht: (2024)

Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
von: Xu, Runhua, et al.
Veröffentlicht: (2025)

Precision Guided Approach to Mitigate Data Poisoning Attacks in Federated Learning
von: Kumar, K Naveen, et al.
Veröffentlicht: (2024)

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
von: Zou, Wei, et al.
Veröffentlicht: (2026)

Defending Against Neural Network Model Inversion Attacks via Data Poisoning
von: Zhou, Shuai, et al.
Veröffentlicht: (2024)

Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
von: Shan, Shawn, et al.
Veröffentlicht: (2023)

MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots
von: Wang, Yuhao, et al.
Veröffentlicht: (2026)

RTBAS: Defending LLM Agents Against Prompt Injection and Privacy Leakage
von: Zhong, Peter Yong, et al.
Veröffentlicht: (2025)

Concept-Aware Privacy Mechanisms for Defending Embedding Inversion Attacks
von: Tsai, Yu-Che, et al.
Veröffentlicht: (2026)

Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems
von: Qu, Yubin, et al.
Veröffentlicht: (2026)

BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning
von: Tie, Guiyao, et al.
Veröffentlicht: (2026)

LoopTrap: Termination Poisoning Attacks on LLM Agents
von: Xu, Huiyu, et al.
Veröffentlicht: (2026)

Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization
von: Liu, Tiantian, et al.
Veröffentlicht: (2024)

SAFELOC: Overcoming Data Poisoning Attacks in Heterogeneous Federated Machine Learning for Indoor Localization
von: Singampalli, Akhil, et al.
Veröffentlicht: (2024)

Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
von: Peng, Wanli, et al.
Veröffentlicht: (2025)

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
von: Di, Jimmy Z., et al.
Veröffentlicht: (2022)

System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection
von: Li, Zongze, et al.
Veröffentlicht: (2025)

Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
von: Choudhary, Sarthak, et al.
Veröffentlicht: (2025)