Copertina

DeepEclipse: How to Break White-Box DNN-Watermarking Schemes

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Pegoraro, Alessandro, Segna, Carlotta, Kumari, Kavita, Sadeghi, Ahmad-Reza
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)
di: Rieger, Phillip, et al.
Pubblicazione: (2025)

FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning
di: Fereidooni, Hossein, et al.
Pubblicazione: (2023)

FreeMark: A Non-Invasive White-Box Watermarking for Deep Neural Networks
di: Chen, Yuzhang, et al.
Pubblicazione: (2024)

Black-Box Detection of Language Model Watermarks
di: Gloaguen, Thibaud, et al.
Pubblicazione: (2024)

NeST: Neuron Selective Tuning for LLM Safety
di: Behrouzi, Sasha, et al.
Pubblicazione: (2026)

Breaking Distortion-free Watermarks in Large Language Models
di: Reynolds, Shayleen, et al.
Pubblicazione: (2025)

Towards Traitor Tracing in Black-and-White-Box DNN Watermarking with Tardos-based Codes
di: Rodriguez-Lois, Elena, et al.
Pubblicazione: (2023)

One for All and All for One: GNN-based Control-Flow Attestation for Embedded Devices
di: Chilese, Marco, et al.
Pubblicazione: (2024)

A Watermark for Black-Box Language Models
di: Bahri, Dara, et al.
Pubblicazione: (2024)

MAED: Mathematical Activation Error Detection for Mitigating Physical Fault Attacks in DNN Inference
di: Ahmadi, Kasra, et al.
Pubblicazione: (2026)

DeepTracer: Tracing Stolen Model via Deep Coupled Watermarks
di: Yang, Yunfei, et al.
Pubblicazione: (2025)

Certifiable Black-Box Attacks with Randomized Adversarial Examples: Breaking Defenses with Provable Confidence
di: Hong, Hanbin, et al.
Pubblicazione: (2023)

PVMark: Enabling Public Verifiability for LLM Watermarking Schemes
di: Duan, Haohua, et al.
Pubblicazione: (2025)

An Attack to Break Permutation-Based Private Third-Party Inference Schemes for LLMs
di: Thomas, Rahul, et al.
Pubblicazione: (2025)

TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding
di: Pagnotta, Giulio, et al.
Pubblicazione: (2022)

DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation
di: Qiu, Han, et al.
Pubblicazione: (2020)

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

BlockDoor: Blocking Backdoor Based Watermarks in Deep Neural Networks
di: Puah, Yi Hao, et al.
Pubblicazione: (2024)

Walma: Learning to See Memory Corruption in WebAssembly
di: Draissi, Oussama, et al.
Pubblicazione: (2026)

Quantization Blindspots: How Model Compression Breaks Backdoor Defenses
di: Pandey, Rohan, et al.
Pubblicazione: (2025)

WhisperFuzz: White-Box Fuzzing for Detecting and Locating Timing Vulnerabilities in Processors
di: Borkar, Pallavi, et al.
Pubblicazione: (2024)

Distortion-free Watermarks are not Truly Distortion-free under Watermark Key Collisions
di: Wu, Yihan, et al.
Pubblicazione: (2024)

Watermarking Generative Categorical Data
di: Gu, Bochao, et al.
Pubblicazione: (2024)

Refined Detection for Gumbel Watermarking
di: Lattimore, Tor
Pubblicazione: (2026)

Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
di: Yao, Yuan, et al.
Pubblicazione: (2025)

SCU: An Efficient Machine Unlearning Scheme for Deep Learning Enabled Semantic Communications
di: Wang, Weiqi, et al.
Pubblicazione: (2025)

Is The Watermarking Of LLM-Generated Code Robust?
di: Suresh, Tarun, et al.
Pubblicazione: (2024)

Signal Watermark on Large Language Models
di: Xu, Zhenyu, et al.
Pubblicazione: (2024)

Towards Watermarking of Open-Source LLMs
di: Gloaguen, Thibaud, et al.
Pubblicazione: (2025)

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

Exploring DNN Robustness Against Adversarial Attacks Using Approximate Multipliers
di: Askarizadeh, Mohammad Javad, et al.
Pubblicazione: (2024)

A White-Box Adversarial Attack Against a Digital Twin
di: Patterson, Wilson, et al.
Pubblicazione: (2022)

FDINet: Protecting against DNN Model Extraction via Feature Distortion Index
di: Yao, Hongwei, et al.
Pubblicazione: (2023)

Exploring the Effect of DNN Depth on Adversarial Attacks in Network Intrusion Detection Systems
di: ElShehaby, Mohamed, et al.
Pubblicazione: (2025)

Ideal Attribution and Faithful Watermarks for Language Models
di: Song, Min Jae, et al.
Pubblicazione: (2025)

Leveraging Optimization for Adaptive Attacks on Image Watermarks
di: Lukas, Nils, et al.
Pubblicazione: (2023)

Traceable Black-box Watermarks for Federated Learning
di: Xu, Jiahao, et al.
Pubblicazione: (2025)

LLM Fingerprinting via Semantically Conditioned Watermarks
di: Gloaguen, Thibaud, et al.
Pubblicazione: (2025)

Robust Spectral Watermark for Synthetic Tabular Data
di: Zhao, Yizhou, et al.
Pubblicazione: (2025)

AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing
di: Zhou, Tong, et al.
Pubblicazione: (2024)