相关论文: Model Unmerging: Making Your Models Unmergeable fo…

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…

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:…

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…

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:…

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…

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…

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…

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…

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…

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…

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…

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)…

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…

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…

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 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…

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…

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…

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…

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…