English
Related papers

Related papers: Model Unmerging: Making Your Models Unmergeable fo…

200 papers

Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular community platforms now offer convenient distribution of a large…

Machine Learning · Computer Science 2024-09-02 Md Rafi Ur Rashid , Jing Liu , Toshiaki Koike-Akino , Shagufta Mehnaz , Ye Wang

Slot-based object-centric learning represents an image as a set of latent slots with a decoder that combines them into an image or features. The decoder specifies how slots are combined into an output, but the slot set is typically fixed:…

Computer Vision and Pattern Recognition · Computer Science 2026-03-13 Christos Chatzisavvas , Panagiotis Rigas , George Ioannakis , Vassilis Katsouros , Nikolaos Mitianoudis

The drastic increase in language models' parameters has led to a new trend of deploying models in cloud servers, raising growing concerns about private inference for Transformer-based models. Existing two-party privacy-preserving…

Computation and Language · Computer Science 2023-12-12 Zi Liang , Pinghui Wang , Ruofei Zhang , Nuo Xu , Lifeng Xing , Shuo Zhang

Modern deep learning usually treats models as separate artifacts: trained independently, specialized for particular purposes, and replaced when improved versions appear. This thesis studies model merging as an alternative paradigm:…

Machine Learning · Computer Science 2026-05-05 Donato Crisostomi

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Cryptography and Security · Computer Science 2025-09-23 Brendan Murphy , Dillon Bowen , Shahrad Mohammadzadeh , Tom Tseng , Julius Broomfield , Adam Gleave , Kellin Pelrine

Large Language Models (LLMs) are increasingly integrated into real-world applications, raising concerns about privacy, security and the need to remove undesirable knowledge. Machine Unlearning has emerged as a promising solution, yet faces…

Machine Learning · Computer Science 2025-10-22 Yisheng Zhong , Zhengbang Yang , Zhuangdi Zhu

Model merging aims to integrate multiple task-adapted models into a unified model that preserves the knowledge of each task. In this paper, we identify that the key to this knowledge retention lies in maintaining the directional consistency…

Machine Learning · Computer Science 2026-03-17 Han-Chen Zhang , Zi-Hao Zhou , Mao-Lin Luo , Shimin Di , Min-Ling Zhang , Tong Wei

In this work, we explore the limitations of combining models by averaging intermediate features, referred to as model merging, and propose a new direction for achieving collective model intelligence through what we call compatible…

Machine Learning · Computer Science 2024-11-05 Jyothish Pari , Samy Jelassi , Pulkit Agrawal

We propose a novel method for protecting trained models with a secret key so that unauthorized users without the correct key cannot get the correct inference. By taking advantage of transfer learning, the proposed method enables us to train…

Machine Learning · Computer Science 2021-03-08 MaungMaung AprilPyone , Hitoshi Kiya

Model merging provides a way of cheaply combining individual models to produce a model that inherits each individual's capabilities. While some merging methods can approach the performance of multitask training, they are often heuristically…

Machine Learning · Computer Science 2026-04-03 Marawan Gamal Abdel Hameed , Derek Tam , Pascal Jr Tikeng Notsawo , Colin Raffel , Guillaume Rabusseau

Model immunization is an emerging direction that aims to mitigate the potential risk of misuse associated with open-sourced models and advancing adaptation methods. The idea is to make the released models' weights difficult to fine-tune on…

Computer Vision and Pattern Recognition · Computer Science 2024-12-23 Amber Yijia Zheng , Raymond A. Yeh

Fine-tuning the large language models (LLMs) are prevented by the deficiency of centralized control and the massive computing and communication overhead on the decentralized schemes. While the typical standard federated learning (FL)…

Machine Learning · Computer Science 2025-08-28 Zehua Cheng , Rui Sun , Jiahao Sun , Yike Guo

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Felix Hsieh , Huy H. Nguyen , AprilPyone MaungMaung , Dmitrii Usynin , Isao Echizen

Model stealing aims at inferring a victim model's functionality at a fraction of the original training cost. While the goal is clear, in practice the model's architecture, weight dimension, and original training data can not be determined…

Machine Learning · Computer Science 2023-08-21 David Pape , Sina Däubener , Thorsten Eisenhofer , Antonio Emanuele Cinà , Lea Schönherr

Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradients and propose a…

Machine Learning · Computer Science 2024-08-26 Nico Daheim , Thomas Möllenhoff , Edoardo Maria Ponti , Iryna Gurevych , Mohammad Emtiyaz Khan

Machine learning is advancing rapidly, with applications bringing notable benefits, such as improvements in translation and code generation. Models like ChatGPT, powered by Large Language Models (LLMs), are increasingly integrated into…

Machine Learning · Computer Science 2025-06-10 Torsten Krauß , Hamid Dashtbani , Alexandra Dmitrienko

Continual Model Merging (CMM) enables rapid customization of foundation models by sequentially incorporating task-adapted models without repeated retraining. However, existing merging rules usually update the deployed model through fixed…

Machine Learning · Computer Science 2026-05-26 Lihong Lin , Haidong Kang

With the widespread adoption of edge computing technologies and the increasing prevalence of deep learning models in these environments, the security risks and privacy threats to models and data have grown more acute. Attackers can exploit…

Cryptography and Security · Computer Science 2024-11-07 Peihao Li

Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. Oftentimes fine-tuned models are readily available but their training data is not, due to data privacy or intellectual property…

Computation and Language · Computer Science 2025-05-23 Xisen Jin , Xiang Ren , Daniel Preotiuc-Pietro , Pengxiang Cheng

Model merging offers a scalable alternative to multi-task learning but often yields suboptimal performance on classification tasks. We attribute this degradation to a geometric misalignment between the merged encoder and static…

Machine Learning · Computer Science 2026-02-03 Fanshuang Kong , Richong Zhang , Zhijie Nie , Hang Zhou , Ziqiao Wang , Qiang Sun , Chunming Hu