Buchumschlag

MEA-Defender: A Robust Watermark against Model Extraction Attack

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Lv, Peizhuo, Ma, Hualong, Chen, Kai, Zhou, Jiachen, Zhang, Shengzhi, Liang, Ruigang, Zhu, Shenchen, Li, Pan, Zhang, Yingjun
Format:	Preprint
Veröffentlicht:	2024
Schlagworte:	Cryptography and Security Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
von: Lv, Peizhuo, et al.
Veröffentlicht: (2022)

LoRAGuard: An Effective Black-box Watermarking Approach for LoRAs
von: Lv, Peizhuo, et al.
Veröffentlicht: (2025)

A Model Stealing Attack Against Multi-Exit Networks
von: Pan, Li, et al.
Veröffentlicht: (2023)

ModelShield: Adaptive and Robust Watermark against Model Extraction Attack
von: Pang, Kaiyi, et al.
Veröffentlicht: (2024)

RAG-WM: An Efficient Black-Box Watermarking Approach for Retrieval-Augmented Generation of Large Language Models
von: Lv, Peizhuo, et al.
Veröffentlicht: (2025)

CNT: Safety-oriented Function Reuse across LLMs via Cross-Model Neuron Transfer
von: Zhao, Yue, et al.
Veröffentlicht: (2026)

Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks
von: Xu, Yixiao, et al.
Veröffentlicht: (2025)

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
von: Chen, Yulin, et al.
Veröffentlicht: (2025)

MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
von: Cheng, Xueqi, et al.
Veröffentlicht: (2025)

Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
von: An, Li, et al.
Veröffentlicht: (2025)

Robust-Wide: Robust Watermarking against Instruction-driven Image Editing
von: Hu, Runyi, et al.
Veröffentlicht: (2024)

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

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

Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss
von: Yang, Guang, et al.
Veröffentlicht: (2024)

Turn-Based Structural Triggers: Prompt-Free Backdoors in Multi-Turn LLMs
von: Lu, Yiyang, et al.
Veröffentlicht: (2026)

Collective Certified Robustness against Graph Injection Attacks
von: Lai, Yuni, et al.
Veröffentlicht: (2024)

ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models
von: Qian, Yuqi, et al.
Veröffentlicht: (2026)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
von: Jiang, Tanqiu, et al.
Veröffentlicht: (2024)

Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models
von: Ma, Jiachen, et al.
Veröffentlicht: (2024)

Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors
von: Koda, Satoru, et al.
Veröffentlicht: (2024)

Dormant: Defending against Pose-driven Human Image Animation
von: Zhou, Jiachen, et al.
Veröffentlicht: (2024)

A Defensive Framework Against Adversarial Attacks on Machine Learning-Based Network Intrusion Detection Systems
von: Tafreshian, Benyamin, et al.
Veröffentlicht: (2025)

VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy
von: Cui, Yu, et al.
Veröffentlicht: (2025)

Optimizing Adaptive Attacks against Watermarks for Language Models
von: Diaa, Abdulrahman, et al.
Veröffentlicht: (2024)

Defending against Data Poisoning Attacks in Federated Learning via User Elimination
von: Galanis, Nick
Veröffentlicht: (2024)

Defending against Backdoor Attack on Deep Neural Networks
von: Cheng, Hao, et al.
Veröffentlicht: (2020)

Invariant Aggregator for Defending against Federated Backdoor Attacks
von: Wang, Xiaoyang, et al.
Veröffentlicht: (2022)

SpeechVerifier: Robust Acoustic Fingerprint against Tampering Attacks via Watermarking
von: Yao, Lingfeng, et al.
Veröffentlicht: (2025)

Backdoor Attacks against Hybrid Classical-Quantum Neural Networks
von: Guo, Ji, et al.
Veröffentlicht: (2024)

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
von: Xue, Lulu, et al.
Veröffentlicht: (2024)

Adversarial Attacks on Reinforcement Learning-based Medical Questionnaire Systems: Input-level Perturbation Strategies and Medical Constraint Validation
von: Liu, Peizhuo
Veröffentlicht: (2025)

Your Agent Can Defend Itself against Backdoor Attacks
von: Changjiang, Li, et al.
Veröffentlicht: (2025)

A Robust Semantics-based Watermark for Large Language Model against Paraphrasing
von: Ren, Jie, et al.
Veröffentlicht: (2023)

An Automated Attack Investigation Approach Leveraging Threat-Knowledge-Augmented Large Language Models
von: Dai, Rujie, et al.
Veröffentlicht: (2025)

PhantomFetch: Obfuscating Loads against Prefetcher Side-Channel Attacks
von: Zhang, Xingzhi, et al.
Veröffentlicht: (2025)

A Game Between the Defender and the Attacker for Trigger-based Black-box Model Watermarking
von: Huang, Chaoyue, et al.
Veröffentlicht: (2025)

Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection
von: Li, Shuai, et al.
Veröffentlicht: (2023)

Secure Goal-Oriented Communication: Defending against Eavesdropping Timing Attacks
von: Mason, Federico, et al.
Veröffentlicht: (2025)

Invariant-based Robust Weights Watermark for Large Language Models
von: Guo, Qingxiao, et al.
Veröffentlicht: (2025)

External Data Extraction Attacks against Retrieval-Augmented Large Language Models
von: He, Yu, et al.
Veröffentlicht: (2025)