Related papers: LoBAM: LoRA-Based Backdoor Attack on Model Merging
Merging multiple Low-Rank Adaptation (LoRA) experts into a single backbone is a promising approach for efficient multi-task deployment. While existing methods strive to alleviate interference via weight interpolation or subspace alignment,…
Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…
Language Models (LMs) typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation (LoRA) has gained the most widespread…
The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…
Model merging leverages multiple finetuned expert models to construct a multi-task model with low cost, and is gaining increasing attention. However, as a growing number of finetuned models become publicly available, concerns about the…
Recently, adversarial attacks for diffusion models as well as their fine-tuning process have been developed rapidly. To prevent the abuse of these attack algorithms from affecting the practical application of diffusion models, it is…
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…
Recently, various merging methods have been proposed to build a multi-task model from task-specific finetuned models without retraining. However, existing methods suffer from a large performance deterioration compared to using multiple…
Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…
Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…
Fine-tuning has proven to be highly effective in adapting pre-trained models to perform better on new desired tasks with minimal data samples. Among the most widely used approaches are reparameterization methods, which update a target…
The recent success of specialized Large Language Models (LLMs) in domains such as mathematical reasoning and coding has led to growing interest in methods for merging these expert LLMs into a unified Mixture-of-Experts (MoE) model, with the…
It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…
The pre-trained language models are continually fine-tuned to better support downstream applications. However, this operation may result in significant performance degeneration on general tasks beyond the targeted domain. To overcome this…
Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…
Diffusion models are state-of-the-art deep learning empowered generative models that are trained based on the principle of learning forward and reverse diffusion processes via progressive noise-addition and denoising. To gain a better…
Large Language Models (LLMs) have transformed code completion tasks, providing context-based suggestions to boost developer productivity in software engineering. As users often fine-tune these models for specific applications, poisoning and…
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 merging is a widespread technology in large language models (LLMs) that integrates multiple task-specific LLMs into a unified one, enabling the merged model to inherit the specialized capabilities of these LLMs. Most task-specific…
As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…