Copertina

Reconstructing Training Data From Real World Models Trained with Transfer Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Oz, Yakir, Yehudai, Gilad, Vardi, Gal, Antebi, Itai, Irani, Michal, Haim, Niv
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

ImpMIA: Leveraging Implicit Bias for Membership Inference Attack
di: Golbari, Yuval, et al.
Pubblicazione: (2025)

Provable Unlearning with Gradient Ascent on Two-Layer ReLU Neural Networks
di: Melamed, Odelia, et al.
Pubblicazione: (2025)

Provable Privacy Attacks on Trained Shallow Neural Networks
di: Smorodinsky, Guy, et al.
Pubblicazione: (2024)

Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning
di: Zhao, Joshua C., et al.
Pubblicazione: (2024)

Privacy-Preserving CNN Training with Transfer Learning: Multiclass Logistic Regression
di: Chiang, John
Pubblicazione: (2023)

The Curse of Recursion: Training on Generated Data Makes Models Forget
di: Shumailov, Ilia, et al.
Pubblicazione: (2023)

Extracting Training Data from Unconditional Diffusion Models
di: Chen, Yunhao, et al.
Pubblicazione: (2024)

Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection
di: Liang, Ziyou, et al.
Pubblicazione: (2024)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
di: Zhang, Yimeng, et al.
Pubblicazione: (2024)

ICAS: Detecting Training Data from Autoregressive Image Generative Models
di: Yu, Hongyao, et al.
Pubblicazione: (2025)

DeiTFake: Deepfake Detection Model using DeiT Multi-Stage Training
di: Kumar, Saksham, et al.
Pubblicazione: (2025)

ZeroPur: Succinct Training-Free Adversarial Purification
di: Liu, Erhu, et al.
Pubblicazione: (2024)

DataFreeShield: Defending Adversarial Attacks without Training Data
di: Lee, Hyeyoon, et al.
Pubblicazione: (2024)

Certified Robustness to Data Poisoning in Gradient-Based Training
di: Sosnin, Philip, et al.
Pubblicazione: (2024)

Training Data Protection with Compositional Diffusion Models
di: Golatkar, Aditya, et al.
Pubblicazione: (2023)

LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data
di: German, Eyal, et al.
Pubblicazione: (2025)

Err on the Side of Texture: Texture Bias on Real Data
di: Hoak, Blaine, et al.
Pubblicazione: (2024)

CIS-BA: Continuous Interaction Space Based Backdoor Attack for Object Detection in the Real-World
di: Zhao, Shuxin, et al.
Pubblicazione: (2025)

SEAL: Semantic Aware Image Watermarking
di: Arabi, Kasra, et al.
Pubblicazione: (2025)

AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstruction
di: Wang, Chao, et al.
Pubblicazione: (2025)

CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training
di: Li, Qi, et al.
Pubblicazione: (2026)

Color Matters: Demosaicing-Guided Color Correlation Training for Generalizable AI-Generated Image Detection
di: Zhong, Nan, et al.
Pubblicazione: (2026)

Training-Free Color-Aware Adversarial Diffusion Sanitization for Diffusion Stegomalware Defense at Security Gateways
di: Frants, Vladimir, et al.
Pubblicazione: (2025)

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
di: Jiang, Tanqiu, et al.
Pubblicazione: (2025)

RoMA: Robust Malware Attribution via Byte-level Adversarial Training with Global Perturbations and Adversarial Consistency Regularization
di: Sun, Yuxia, et al.
Pubblicazione: (2025)

The Impact of Scaling Training Data on Adversarial Robustness
di: Zimmerli, Marco, et al.
Pubblicazione: (2025)

CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training
di: Chen, Yuxi, et al.
Pubblicazione: (2026)

Model Inversion Robustness: Can Transfer Learning Help?
di: Ho, Sy-Tuyen, et al.
Pubblicazione: (2024)

Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization
di: Qiu, Yixiang, et al.
Pubblicazione: (2025)

Training-Free Watermarking for Autoregressive Image Generation
di: Tong, Yu, et al.
Pubblicazione: (2025)

ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers
di: Cao, Hanwen, et al.
Pubblicazione: (2025)

Towards an End-to-End (E2E) Adversarial Learning and Application in the Physical World
di: Biton, Dudi, et al.
Pubblicazione: (2025)

Solutions to Deepfakes: Can Camera Hardware, Cryptography, and Deep Learning Verify Real Images?
di: Vilesov, Alexander, et al.
Pubblicazione: (2024)

SAT-LDM: Provably Generalizable Image Watermarking for Latent Diffusion Models with Self-Augmented Training
di: Zhang, Lu, et al.
Pubblicazione: (2024)

One Prompt to Verify Your Models: Black-Box Text-to-Image Models Verification via Non-Transferable Adversarial Attacks
di: Guo, Ji, et al.
Pubblicazione: (2024)

SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation
di: Chung, Yunsung, et al.
Pubblicazione: (2025)

Adversarial Training against Location-Optimized Adversarial Patches
di: Rao, Sukrut, et al.
Pubblicazione: (2020)

Fully Exploiting Every Real Sample: SuperPixel Sample Gradient Model Stealing
di: Zhao, Yunlong, et al.
Pubblicazione: (2024)

MALT Powers Up Adversarial Attacks
di: Melamed, Odelia, et al.
Pubblicazione: (2024)

DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
di: Wang, Hanrui, et al.
Pubblicazione: (2025)