Image de couverture de livre

Recovering the Pre-Fine-Tuning Weights of Generative Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Horwitz, Eliahu, Kahana, Jonathan, Hoshen, Yedid
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Computation and Language Cryptography and Security Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights
par: Kahana, Jonathan, et autres
Publié: (2025)

Deep Linear Probe Generators for Weight Space Learning
par: Kahana, Jonathan, et autres
Publié: (2024)

Learning on Model Weights using Tree Experts
par: Horwitz, Eliahu, et autres
Publié: (2024)

We Should Chart an Atlas of All the World's Models
par: Horwitz, Eliahu, et autres
Publié: (2025)

Discovering Hidden Gems in Model Repositories
par: Kahana, Jonathan, et autres
Publié: (2026)

Dataset Size Recovery from LoRA Weights
par: Salama, Mohammad, et autres
Publié: (2024)

Distilling Datasets Into Less Than One Image
par: Shul, Asaf, et autres
Publié: (2024)

Risks When Sharing LoRA Fine-Tuned Diffusion Model Weights
par: Yao, Dixi
Publié: (2024)

Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
par: Singh, Naman Deep, et autres
Publié: (2024)

DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning
par: Lebensold, Jonathan, et autres
Publié: (2024)

Differentially Private Bias-Term Fine-tuning of Foundation Models
par: Bu, Zhiqi, et autres
Publié: (2022)

Real-Time Deepfake Detection in the Real-World
par: Cavia, Bar, et autres
Publié: (2024)

To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model
par: Zhao, Chengshuai, et autres
Publié: (2026)

Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models
par: Ding, Yi, et autres
Publié: (2025)

Jailbreaking Attack against Multimodal Large Language Model
par: Niu, Zhenxing, et autres
Publié: (2024)

Few-Shot Adversarial Prompt Learning on Vision-Language Models
par: Zhou, Yiwei, et autres
Publié: (2024)

Meta-Unlearning on Diffusion Models: Preventing Relearning Unlearned Concepts
par: Gao, Hongcheng, et autres
Publié: (2024)

VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models
par: Liao, Qilin, et autres
Publié: (2025)

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
par: Jin, Haibo, et autres
Publié: (2024)

JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models
par: Jin, Haibo, et autres
Publié: (2024)

Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting
par: Chin, Zhi-Yi, et autres
Publié: (2024)

An Attribute-based Method for Video Anomaly Detection
par: Reiss, Tal, et autres
Publié: (2022)

Solving Trojan Detection Competitions with Linear Weight Classification
par: Huster, Todd, et autres
Publié: (2024)

ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test
par: Yang, Guan-Yan, et autres
Publié: (2025)

Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
par: Wang, Hao, et autres
Publié: (2024)

Dissecting Adversarial Robustness of Multimodal LM Agents
par: Wu, Chen Henry, et autres
Publié: (2024)

Defending Our Privacy With Backdoors
par: Hintersdorf, Dominik, et autres
Publié: (2023)

Towards hyperparameter-free optimization with differential privacy
par: Bu, Zhiqi, et autres
Publié: (2025)

The Curse of Recursion: Training on Generated Data Makes Models Forget
par: Shumailov, Ilia, et autres
Publié: (2023)

T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
par: Miao, Yibo, et autres
Publié: (2024)

On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlook
par: Fan, Mingyuan, et autres
Publié: (2023)

Benchmarking Large Multimodal Models against Common Corruptions
par: Zhang, Jiawei, et autres
Publié: (2024)

Test-Time Backdoor Attacks on Multimodal Large Language Models
par: Lu, Dong, et autres
Publié: (2024)

Tuning for Two Adversaries: Enhancing the Robustness Against Transfer and Query-Based Attacks using Hyperparameter Tuning
par: Zimmer, Pascal, et autres
Publié: (2025)

R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
par: Sheng, Lijun, et autres
Publié: (2025)

Explainable Adversarial Attacks on Coarse-to-Fine Classifiers
par: Heidarizadeh, Akram, et autres
Publié: (2025)

Assessing Neural Network Robustness via Adversarial Pivotal Tuning
par: Christensen, Peter Ebert, et autres
Publié: (2022)

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
par: Lin, Weilin, et autres
Publié: (2024)

Watermark-based Attribution of AI-Generated Content
par: Jiang, Zhengyuan, et autres
Publié: (2024)

ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
par: Yao, Xin, et autres
Publié: (2025)