Imagen de Portada

Osmosis Distillation: Model Hijacking with the Fewest Samples

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Shi, Yuchen, Chen, Huajie, Xu, Heng, Liu, Zhiquan, Shen, Jialiang, Liu, Chi, Zhou, Shuai, Zhu, Tianqing, Zhou, Wanlei
Formato:	Preprint
Publicado:	2026
Materias:	Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Turning Black Box into White Box: Dataset Distillation Leaks
por: Chen, Huajie, et al.
Publicado: (2026)

Really Unlearned? Verifying Machine Unlearning via Influential Sample Pairs
por: Xu, Heng, et al.
Publicado: (2024)

Evaluating of Machine Unlearning: Robustness Verification Without Prior Modifications
por: Xu, Heng, et al.
Publicado: (2024)

CSC: Turning the Adversary's Poison against Itself
por: Shi, Yuchen, et al.
Publicado: (2026)

Forgetting Similar Samples: Can Machine Unlearning Do it Better?
por: Xu, Heng, et al.
Publicado: (2026)

Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor
por: Chang, Wenhan, et al.
Publicado: (2026)

Towards Efficient Target-Level Machine Unlearning Based on Essential Graph
por: Xu, Heng, et al.
Publicado: (2024)

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

Don't Forget Too Much: Towards Machine Unlearning on Feature Level
por: Xu, Heng, et al.
Publicado: (2024)

Towards Robust GAN-generated Image Detection: a Multi-view Completion Representation
por: Liu, Chi, et al.
Publicado: (2023)

Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation
por: Xu, Heng, et al.
Publicado: (2024)

QUEEN: Query Unlearning against Model Extraction
por: Chen, Huajie, et al.
Publicado: (2024)

Privacy Intelligence: A Survey on Image Privacy in Online Social Networks
por: Liu, Chi, et al.
Publicado: (2020)

Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection
por: Liu, Chi, et al.
Publicado: (2025)

How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers
por: Zhang, Guangsheng, et al.
Publicado: (2022)

Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction
por: Chen, Huajie, et al.
Publicado: (2026)

Zero-shot Class Unlearning via Layer-wise Relevance Analysis and Neuronal Path Perturbation
por: Chang, Wenhan, et al.
Publicado: (2024)

Reinforcement Unlearning
por: Ye, Dayong, et al.
Publicado: (2023)

Linkage on Security, Privacy and Fairness in Federated Learning: New Balances and New Perspectives
por: Wang, Linlin, et al.
Publicado: (2024)

When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks
por: Tian, Huan, et al.
Publicado: (2023)

Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
por: Wang, Linlin, et al.
Publicado: (2025)

Large Language Model Federated Learning with Blockchain and Unlearning for Cross-Organizational Collaboration
por: Zuo, Xuhan, et al.
Publicado: (2024)

Large Language Models for Link Stealing Attacks Against Graph Neural Networks
por: Guan, Faqian, et al.
Publicado: (2024)

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions
por: Qi, Minfeng, et al.
Publicado: (2026)

The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies
por: He, Feng, et al.
Publicado: (2024)

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?
por: Wang, Shang, et al.
Publicado: (2024)

Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey
por: Wang, Shang, et al.
Publicado: (2024)

Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks
por: Guan, Faqian, et al.
Publicado: (2024)

Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
por: Zhang, Guangsheng, et al.
Publicado: (2026)

Seed Hijacking of LLM Sampling and Quantum Random Number Defense
por: You, Ziyang, et al.
Publicado: (2026)

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
por: Yuan, Zenghui, et al.
Publicado: (2025)

Model Hijacking Attack in Federated Learning
por: Li, Zheng, et al.
Publicado: (2024)

Hijacking Large Language Models via Adversarial In-Context Learning
por: Zhou, Xiangyu, et al.
Publicado: (2023)

Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach
por: Qi, Minfeng, et al.
Publicado: (2025)

Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI
por: Ye, Dayong, et al.
Publicado: (2025)

Federated TrustChain: Blockchain-Enhanced LLM Training and Unlearning
por: Zuo, Xuhan, et al.
Publicado: (2024)

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation
por: Liu, Zhichao, et al.
Publicado: (2026)

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models
por: Liang, Jiacheng, et al.
Publicado: (2025)

Federated Learning with Blockchain-Enhanced Machine Unlearning: A Trustworthy Approach
por: Zuo, Xuhan, et al.
Publicado: (2024)

Chain-of-Lure: A Universal Jailbreak Attack Framework using Unconstrained Synthetic Narratives
por: Chang, Wenhan, et al.
Publicado: (2025)