Image de couverture de livre

GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Abdalla, Amro, Shaheen, Ismail, DeGenaro, Dan, Mallick, Rupayan, Raita, Bogdan, Bargal, Sarah Adel
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

FaithFill: Faithful Inpainting for Object Completion Using a Single Reference Image
par: Mallick, Rupayan, et autres
Publié: (2024)

ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models
par: Dong, Sibo, et autres
Publié: (2025)

Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data
par: DeGenaro, Dan, et autres
Publié: (2026)

Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy
par: Yu, Hao, et autres
Publié: (2025)

GenEAva: Generating Cartoon Avatars with Fine-Grained Facial Expressions from Realistic Diffusion-based Faces
par: Yu, Hao, et autres
Publié: (2025)

D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition
par: Mallick, Rupayan, et autres
Publié: (2025)

Task Arithmetic with Support Languages for Low-Resource ASR
par: Rafkin, Emma, et autres
Publié: (2026)

Quasiconvexity and self-improving size estimates
par: Raiţă, Bogdan
Publié: (2025)

Evaluating Concept Filtering Defenses against Child Sexual Abuse Material Generation by Text-to-Image Models
par: Cretu, Ana-Maria, et autres
Publié: (2025)

Semialgebric rank-one convex hulls: 2x2 triangular matrices and beyond
par: Meroni, Chiara, et autres
Publié: (2025)

Partial regularity and higher integrability for A-quasiconvex variational problems
par: Li, Zhuolin, et autres
Publié: (2024)

Comparison of polynomial matrix differential operators
par: Curcă, Eduard, et autres
Publié: (2026)

GIFT: Global stabilisation via Intrinsic Fine Tuning
par: Young, Rory, et autres
Publié: (2026)

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
par: Ruan, Zhiwen, et autres
Publié: (2026)

Syzygies, constant rank, and beyond
par: Härkönen, Marc, et autres
Publié: (2021)

Partial regularity for $\mathscr{A}$-quasiconvex variational problems of linear growth
par: Irving, Christopher, et autres
Publié: (2026)

Compensation phenomena for concentration effects via nonlinear elliptic estimates
par: Guerra, André, et autres
Publié: (2021)

CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning
par: ElZemity, Adel, et autres
Publié: (2025)

GIFT: Guided Importance-Aware Fine-Tuning for Diffusion Language Models
par: Xu, Guowei, et autres
Publié: (2025)

Boundary ellipticity and limiting $L^1$-estimates on halfspaces
par: Gmeineder, Franz, et autres
Publié: (2022)

Gaussian Process Regression for Inverse Problems in Linear PDEs
par: Li, Xin, et autres
Publié: (2025)

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs
par: Zhelnin, Maxim, et autres
Publié: (2024)

GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA
par: Wang, Zhichao
Publié: (2025)

On Scaling Properties for a Class of Two-Well Problems for Higher Order Homogeneous Linear Differential Operators
par: Raiţă, Bogdan, et autres
Publié: (2023)

Multi-concept Model Immunization through Differentiable Model Merging
par: Zheng, Amber Yijia, et autres
Publié: (2024)

Immunization against harmful fine-tuning attacks
par: Rosati, Domenic, et autres
Publié: (2024)

Gaussian Process Priors for Boundary Value Problems of Linear Partial Differential Equations
par: Huang, Jianlei, et autres
Publié: (2024)

Crates.io malicious packages
par: Cornelissen, Eric
Publié: (2026)

Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
par: Zhang, Jianwei, et autres
Publié: (2026)

IMMA: Immunizing text-to-image Models against Malicious Adaptation
par: Zheng, Amber Yijia, et autres
Publié: (2023)

The peculiar response of Kelvin-Voigt chains with a free end
par: Saha, Rupayan, et autres
Publié: (2026)

Semaglutide‐Induced Hepatic Injury: A Rare Case of Drug Induced Liver Injury
par: Rupayan Kundu, et autres
Publié: (2025)

Immunization against dengue virus infection is coercive: A timely call
par: Iftekhar Ahmed, et autres
Publié: (2024)

Immunization against Medically Important Human Coronaviruses of Public Health Concern
par: Nabil A. Nimer, et autres
Publié: (2024)

Process Tracking for Dynamic Tuning Applications on the Grid
par: Genaro Costa
Publié: (2007)

Comparing EPGP Surrogates and Finite Elements Under Degree-of-Freedom Parity
par: Amo, Obed, et autres
Publié: (2025)

Immunization of cultured shrimp against WSSV by use of produced recombinant vaccine(In Vitro)
par: Houshmand, Hossein, et autres
Publié: (2015)

INFERMAL: Inferential analysis of maliciously registered domains
par: Nosyk, Yevheniya, et autres
Publié: (2025)

Anatomy of an AI-powered malicious social botnet
par: Yang, Kai-Cheng, et autres
Publié: (2023)

Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning
par: Abdalla, M. H. I., et autres
Publié: (2025)