Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Abdalla, Amro, Shaheen, Ismail, DeGenaro, Dan, Mallick, Rupayan, Raita, Bogdan, Bargal, Sarah Adel
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FaithFill: Faithful Inpainting for Object Completion Using a Single Reference Image
by: Mallick, Rupayan, et al.
Published: (2024)

ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models
by: Dong, Sibo, et al.
Published: (2025)

Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data
by: DeGenaro, Dan, et al.
Published: (2026)

Gen-AFFECT: Generation of Avatar Fine-grained Facial Expressions with Consistent identiTy
by: Yu, Hao, et al.
Published: (2025)

GenEAva: Generating Cartoon Avatars with Fine-Grained Facial Expressions from Realistic Diffusion-based Faces
by: Yu, Hao, et al.
Published: (2025)

D-Feat Occlusions: Diffusion Features for Robustness to Partial Visual Occlusions in Object Recognition
by: Mallick, Rupayan, et al.
Published: (2025)

Task Arithmetic with Support Languages for Low-Resource ASR
by: Rafkin, Emma, et al.
Published: (2026)

Quasiconvexity and self-improving size estimates
by: Raiţă, Bogdan
Published: (2025)

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

Semialgebric rank-one convex hulls: 2x2 triangular matrices and beyond
by: Meroni, Chiara, et al.
Published: (2025)

Partial regularity and higher integrability for A-quasiconvex variational problems
by: Li, Zhuolin, et al.
Published: (2024)

Comparison of polynomial matrix differential operators
by: Curcă, Eduard, et al.
Published: (2026)

GIFT: Global stabilisation via Intrinsic Fine Tuning
by: Young, Rory, et al.
Published: (2026)

GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
by: Ruan, Zhiwen, et al.
Published: (2026)

Syzygies, constant rank, and beyond
by: Härkönen, Marc, et al.
Published: (2021)

Partial regularity for $\mathscr{A}$-quasiconvex variational problems of linear growth
by: Irving, Christopher, et al.
Published: (2026)

Compensation phenomena for concentration effects via nonlinear elliptic estimates
by: Guerra, André, et al.
Published: (2021)

CyberLLMInstruct: A Pseudo-malicious Dataset Revealing Safety-performance Trade-offs in Cyber Security LLM Fine-tuning
by: ElZemity, Adel, et al.
Published: (2025)

GIFT: Guided Importance-Aware Fine-Tuning for Diffusion Language Models
by: Xu, Guowei, et al.
Published: (2025)

Boundary ellipticity and limiting $L^1$-estimates on halfspaces
by: Gmeineder, Franz, et al.
Published: (2022)

Gaussian Process Regression for Inverse Problems in Linear PDEs
by: Li, Xin, et al.
Published: (2025)

GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMs
by: Zhelnin, Maxim, et al.
Published: (2024)

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

On Scaling Properties for a Class of Two-Well Problems for Higher Order Homogeneous Linear Differential Operators
by: Raiţă, Bogdan, et al.
Published: (2023)

Multi-concept Model Immunization through Differentiable Model Merging
by: Zheng, Amber Yijia, et al.
Published: (2024)

Immunization against harmful fine-tuning attacks
by: Rosati, Domenic, et al.
Published: (2024)

Gaussian Process Priors for Boundary Value Problems of Linear Partial Differential Equations
by: Huang, Jianlei, et al.
Published: (2024)

Crates.io malicious packages
by: Cornelissen, Eric
Published: (2026)

Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
by: Zhang, Jianwei, et al.
Published: (2026)

IMMA: Immunizing text-to-image Models against Malicious Adaptation
by: Zheng, Amber Yijia, et al.
Published: (2023)

The peculiar response of Kelvin-Voigt chains with a free end
by: Saha, Rupayan, et al.
Published: (2026)

Semaglutide‐Induced Hepatic Injury: A Rare Case of Drug Induced Liver Injury
by: Rupayan Kundu, et al.
Published: (2025)

Immunization against dengue virus infection is coercive: A timely call
by: Iftekhar Ahmed, et al.
Published: (2024)

Immunization against Medically Important Human Coronaviruses of Public Health Concern
by: Nabil A. Nimer, et al.
Published: (2024)

Process Tracking for Dynamic Tuning Applications on the Grid
by: Genaro Costa
Published: (2007)

Comparing EPGP Surrogates and Finite Elements Under Degree-of-Freedom Parity
by: Amo, Obed, et al.
Published: (2025)

Immunization of cultured shrimp against WSSV by use of produced recombinant vaccine(In Vitro)
by: Houshmand, Hossein, et al.
Published: (2015)

INFERMAL: Inferential analysis of maliciously registered domains
by: Nosyk, Yevheniya, et al.
Published: (2025)

Anatomy of an AI-powered malicious social botnet
by: Yang, Kai-Cheng, et al.
Published: (2023)

Zhyper: Factorized Hypernetworks for Conditioned LLM Fine-Tuning
by: Abdalla, M. H. I., et al.
Published: (2025)