English
Related papers

Related papers: When Safe Models Merge into Danger: Exploiting Lat…

200 papers

Model merging offers an efficient way to combine pre-trained neural networks but often suffers from inconsistent performance, especially when merging models with different initializations. We identify the ``vanishing feature'' phenomenon,…

Machine Learning · Computer Science 2025-02-28 Xingyu Qu , Samuel Horvath

LLMs remain vulnerable to jailbreak attacks that exploit adversarial prompts to circumvent safety measures. Current safety fine-tuning approaches face two critical limitations. First, they often fail to strike a balance between security and…

Cryptography and Security · Computer Science 2025-12-23 Yingjie Zhang , Tong Liu , Zhe Zhao , Guozhu Meng , Kai Chen

Model merging aims to combine multiple expert models into a more capable single model, offering benefits such as reduced storage and serving costs, improved generalization, and support for decentralized model development. Despite its…

Machine Learning · Computer Science 2024-10-07 Prateek Yadav , Tu Vu , Jonathan Lai , Alexandra Chronopoulou , Manaal Faruqui , Mohit Bansal , Tsendsuren Munkhdalai

The recent success of machine learning (ML) has been fueled by the increasing availability of computing power and large amounts of data in many different applications. However, the trustworthiness of the resulting models can be compromised…

Cryptography and Security · Computer Science 2024-03-11 Antonio Emanuele Cinà , Kathrin Grosse , Ambra Demontis , Battista Biggio , Fabio Roli , Marcello Pelillo

Deep model fusion/merging is an emerging technique that merges the parameters or predictions of multiple deep learning models into a single one. It combines the abilities of different models to make up for the biases and errors of a single…

Machine Learning · Computer Science 2023-09-28 Weishi Li , Yong Peng , Miao Zhang , Liang Ding , Han Hu , Li Shen

Large Language Models (LLMs) rapidly reshape modern life, advancing fields from healthcare to education and beyond. However, alongside their remarkable capabilities lies a significant threat: the susceptibility of these models to…

Computation and Language · Computer Science 2025-05-16 Michael Fire , Yitzhak Elbazis , Adi Wasenstein , Lior Rokach

Large Language Models (LLMs), now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models…

Cryptography and Security · Computer Science 2025-08-05 Kang Chen , Xiuze Zhou , Yuanguo Lin , Jinhe Su , Yuanhui Yu , Li Shen , Fan Lin

In recent years, Large Language Models (LLMs) have garnered considerable attention for their remarkable abilities in natural language processing tasks. However, their widespread adoption has raised concerns pertaining to trust and safety.…

Artificial Intelligence · Computer Science 2025-07-01 Doohee You , Dan Chon

Large language models (LLMs) have exhibited remarkable versatility and adaptability, while their widespread adoption across various applications also raises critical safety concerns. This paper focuses on the impact of backdoored LLMs.…

Computation and Language · Computer Science 2025-09-03 Jiyang Qiu , Xinbei Ma , Zhuosheng Zhang , Hai Zhao , Yun Li , Qianren Wang

The rapid integration of Generative AI (GenAI) and Large Language Models (LLMs) in sectors such as education and healthcare have marked a significant advancement in technology. However, this growth has also led to a largely unexplored…

Cryptography and Security · Computer Science 2024-03-20 Tri Nguyen , Huong Nguyen , Ahmad Ijaz , Saeid Sheikhi , Athanasios V. Vasilakos , Panos Kostakos

With the rapid growth of deep learning, there is an increasing availability of open-source models for various tasks. However, single fine-tuned models often fall short of meeting the diverse needs of users. Model merging has thus emerged as…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Shenghe Zheng , Hongzhi Wang

Many machine learning models are fine-tuned from large language models (LLMs) to achieve high performance in specialized domains like code generation, biomedical analysis, and mathematical problem solving. However, this fine-tuning process…

Computation and Language · Computer Science 2025-11-14 Jialin Wu , Kecen Li , Zhicong Huang , Xinfeng Li , Xiaofeng Wang , Cheng Hong

LLM applications (i.e., LLM apps) leverage the powerful capabilities of LLMs to provide users with customized services, revolutionizing traditional application development. While the increasing prevalence of LLM-powered applications…

Cryptography and Security · Computer Science 2025-12-17 Yunyi Zhang , Shibo Cui , Baojun Liu , Jingkai Yu , Min Zhang , Fan Shi , Han Zheng

Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This paper sheds light on the security and safety implications of…

Cryptography and Security · Computer Science 2023-08-21 Xiangyu Qi , Kaixuan Huang , Ashwinee Panda , Peter Henderson , Mengdi Wang , Prateek Mittal

Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…

Cryptography and Security · Computer Science 2025-08-07 Xiaohu Li , Yunfeng Ning , Zepeng Bao , Mayi Xu , Jianhao Chen , Tieyun Qian

Federated Learning (FL) is increasingly being adopted in military collaborations to develop Large Language Models (LLMs) while preserving data sovereignty. However, prompt injection attacks-malicious manipulations of input prompts-pose new…

Machine Learning · Computer Science 2026-05-05 Youngjoon Lee , Taehyun Park , Yunho Lee , Jinu Gong , Joonhyuk Kang

The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses…

Artificial Intelligence · Computer Science 2024-12-18 Yifan Yang , Qiao Jin , Furong Huang , Zhiyong Lu

The emergence of Vision Language Models (VLMs) is a significant advancement in integrating computer vision with Large Language Models (LLMs) to produce detailed text descriptions based on visual inputs, yet it introduces new security…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Weimin Lyu , Lu Pang , Tengfei Ma , Haibin Ling , Chao Chen

Large language models (LLMs) are increasingly deployed in real-world applications, raising concerns about their security. While jailbreak attacks highlight failures under overtly harmful queries, they overlook a critical risk: incorrectly…

Cryptography and Security · Computer Science 2025-06-10 Yukai Zhou , Sibei Yang , Wenjie Wang

Fine-tuning of Large Language Models (LLMs) has become the default practice for improving model performance on a given task. However, performance improvement comes at the cost of training on vast amounts of annotated data which could be…

Computation and Language · Computer Science 2025-04-25 Jose G. Moreno , Jesus Lovon , M'Rick Robin-Charlet , Christine Damase-Michel , Lynda Tamine