English
Related papers

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

200 papers

While LLMs excel at general tasks, they struggle in specialized domains like finance, requiring diverse skills in domain knowledge, mathematical reasoning, and multilingual processing. Merging domain-specific Continual Pre-training (CPT)…

Computation and Language · Computer Science 2025-11-05 Kentaro Ueda , François Portet , Hirohiko Suwa , Keiichi Yasumoto

Multimodal Large Language Models (MLLMs) rely on multimodal pre-training over diverse data sources, where different datasets often induce complementary cross-modal alignment capabilities. Model merging provides a cost-effective mechanism…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Zibo Shao , Baochen Xiong , Xiaoshan Yang , Yaguang Song , Qimeng Zhang , Haifeng Chen , Changsheng Xu

Trojan attacks are sophisticated training-time attacks on neural networks that embed backdoor triggers which force the network to produce a specific output on any input which includes the trigger. With the increasing relevance of deep…

Machine Learning · Computer Science 2025-12-16 Xihe Gu , Greg Fields , Yaman Jandali , Tara Javidi , Farinaz Koushanfar

Prompt injection attack, where an attacker injects a prompt into the original one, aiming to make an Large Language Model (LLM) follow the injected prompt to perform an attacker-chosen task, represent a critical security threat. Existing…

Cryptography and Security · Computer Science 2025-09-16 Zedian Shao , Hongbin Liu , Jaden Mu , Neil Zhenqiang Gong

Large language models (LLMs) are increasingly deployed as the service backend for LLM-integrated applications such as code completion and AI-powered search. LLM-integrated applications serve as middleware to refine users' queries with…

Cryptography and Security · Computer Science 2023-11-30 Fengqing Jiang , Zhangchen Xu , Luyao Niu , Boxin Wang , Jinyuan Jia , Bo Li , Radha Poovendran

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

Cryptography and Security · Computer Science 2024-12-25 Caishuang Huang , Wanxu Zhao , Rui Zheng , Huijie Lv , Wenyu Zhan , Shihan Dou , Sixian Li , Xiao Wang , Enyu Zhou , Junjie Ye , Yuming Yang , Tao Gui , Qi Zhang , Xuanjing Huang

A central goal of LLM alignment is to balance helpfulness with harmlessness, yet these objectives conflict when the same knowledge serves both legitimate and malicious purposes. This tension is amplified by context-sensitive alignment: we…

Cryptography and Security · Computer Science 2026-04-20 Ki Sen Hung , Xi Yang , Chang Liu , Haoran Li , Kejiang Chen , Changxuan Fan , Tsun On Kwok , Weiming Zhang , Xiaomeng Li , Yangqiu Song

Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak…

Cryptography and Security · Computer Science 2025-12-18 Yixin Tan , Zhe Yu , Jun Sakuma

Model merging under unseen test-time distribution shifts often renders naive strategies, such as mean averaging unreliable. This challenge is especially acute in medical imaging, where models are fine-tuned locally at clinics on private…

Machine Learning · Computer Science 2026-02-26 Sameer Ambekar , Reza Nasirigerdeh , Peter J. Schuffler , Lina Felsner , Daniel M. Lang , Julia A. Schnabel

Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the models are trained on…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Yi-Lin Sung , Linjie Li , Kevin Lin , Zhe Gan , Mohit Bansal , Lijuan Wang

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to…

Computation and Language · Computer Science 2024-06-07 Javier Rando , Francesco Croce , Kryštof Mitka , Stepan Shabalin , Maksym Andriushchenko , Nicolas Flammarion , Florian Tramèr

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…

Cryptography and Security · Computer Science 2021-01-21 Ximing Qiao , Yuhua Bai , Siping Hu , Ang Li , Yiran Chen , Hai Li

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

Recently, large language models (LLMs) have been gaining a lot of interest due to their adaptability and extensibility in emerging applications, including communication networks. It is anticipated that ZSM networks will be able to support…

Cryptography and Security · Computer Science 2025-01-07 Sunder Ali Khowaja , Parus Khuwaja , Kapal Dev , Hussam Al Hamadi , Engin Zeydan

Open-weight large language models (LLMs) unlock huge benefits in innovation, personalization, privacy, and democratization. However, their core advantage - modifiability - opens the door to systemic risks: bad actors can trivially subvert…

Computers and Society · Computer Science 2025-07-17 Ann-Kathrin Dombrowski , Dillon Bowen , Adam Gleave , Chris Cundy

In recent years, the security vulnerabilities of Multi-modal Large Language Models (MLLMs) have become a serious concern in the Generative Artificial Intelligence (GenAI) research. These highly intelligent models, capable of performing…

Cryptography and Security · Computer Science 2026-01-12 Badhan Chandra Das , Md Tasnim Jawad , Joaquin Molto , M. Hadi Amini , Yanzhao Wu

Today's generative models are capable of synthesizing high-fidelity images, but each model specializes on a specific target domain. This raises the need for model merging: combining two or more pretrained generative models into a single…

Machine Learning · Computer Science 2023-03-21 Omri Avrahami , Dani Lischinski , Ohad Fried

Federated learning (FL) enables a set of entities to collaboratively train a machine learning model without sharing their sensitive data, thus, mitigating some privacy concerns. However, an increasing number of works in the literature…

Cryptography and Security · Computer Science 2022-01-04 Aidmar Wainakh , Ephraim Zimmer , Sandeep Subedi , Jens Keim , Tim Grube , Shankar Karuppayah , Alejandro Sanchez Guinea , Max Mühlhäuser

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Machine Learning · Computer Science 2025-05-16 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu