English
Related papers

Related papers: Vera Verto: Multimodal Hijacking Attack

200 papers

Machine learning (ML) has established itself as a cornerstone for various critical applications ranging from autonomous driving to authentication systems. However, with this increasing adoption rate of machine learning models, multiple…

Cryptography and Security · Computer Science 2021-11-09 Ahmed Salem , Michael Backes , Yang Zhang

Machine learning (ML), driven by prominent paradigms such as centralized and federated learning, has made significant progress in various critical applications ranging from autonomous driving to face recognition. However, its remarkable…

Cryptography and Security · Computer Science 2024-08-06 Zheng Li , Siyuan Wu , Ruichuan Chen , Paarijaat Aditya , Istemi Ekin Akkus , Manohar Vanga , Min Zhang , Hao Li , Yang Zhang

Machine learning has progressed significantly in various applications ranging from face recognition to text generation. However, its success has been accompanied by different attacks. Recently a new attack has been proposed which raises…

Cryptography and Security · Computer Science 2023-05-15 Wai Man Si , Michael Backes , Yang Zhang , Ahmed Salem

Model hijacking can cause significant accountability and security risks since the owner of a hijacked model can be framed for having their model offer illegal or unethical services. Prior works consider model hijacking as a training time…

Cryptography and Security · Computer Science 2025-04-15 Mahmoud Ghorbel , Halima Bouzidi , Ioan Marius Bilasco , Ihsen Alouani

The fast advancements in Large Language Models (LLMs) are driving an increasing number of applications. Together with the growing number of users, we also see an increasing number of attackers who try to outsmart these systems. They want…

Cryptography and Security · Computer Science 2024-05-31 Patrick Levi , Christoph P. Neumann

In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance introduces vulnerabilities to model hijacking attacks, where…

Cryptography and Security · Computer Science 2024-12-23 Xing He , Jiahao Chen , Yuwen Pu , Qingming Li , Chunyi Zhou , Yingcai Wu , Jinbao Li , Shouling Ji

Model merging for Large Language Models (LLMs) directly fuses the parameters of different models finetuned on various tasks, creating a unified model for multi-domain tasks. However, due to potential vulnerabilities in models available on…

Cryptography and Security · Computer Science 2025-05-30 Zenghui Yuan , Yangming Xu , Jiawen Shi , Pan Zhou , Lichao Sun

Are foundation models secure against malicious actors? In this work, we focus on the image input to a vision-language model (VLM). We discover image hijacks, adversarial images that control the behaviour of VLMs at inference time, and…

Machine Learning · Computer Science 2024-09-19 Luke Bailey , Euan Ong , Stuart Russell , Scott Emmons

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Xiaosen Wang , Shaokang Wang , Zhijin Ge , Yuyang Luo , Shudong Zhang

Recently, Large Multi-modal Models (LMMs) have demonstrated their ability to understand the visual contents of images given the instructions regarding the images. Built upon the Large Language Models (LLMs), LMMs also inherit their…

Artificial Intelligence · Computer Science 2024-05-14 Joonhyun Jeong

Machine Learning is becoming a pivotal aspect of many systems today, offering newfound performance on classification and prediction tasks, but this rapid integration also comes with new unforeseen vulnerabilities. To harden these systems…

Cryptography and Security · Computer Science 2022-02-22 Ahmed Abdou , Ryan Sheatsley , Yohan Beugin , Tyler Shipp , Patrick McDaniel

Machine learning models are known to be vulnerable to adversarial attacks, but traditional attacks have mostly focused on single-modalities. With the rise of large multi-modal models (LMMs) like CLIP, which combine vision and language…

Machine Learning · Computer Science 2024-10-18 Arka Daw , Megan Hong-Thanh Chung , Maria Mahbub , Amir Sadovnik

Goal hijacking is a type of adversarial attack on Large Language Models (LLMs) where the objective is to manipulate the model into producing a specific, predetermined output, regardless of the user's original input. In goal hijacking, an…

Computation and Language · Computer Science 2026-03-12 Zheng Chen , Buhui Yao

With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted…

Computer Vision and Pattern Recognition · Computer Science 2025-06-19 Yu Wang , Xiaofei Zhou , Yichen Wang , Geyuan Zhang , Tianxing He

Recently, Multimodal Large Language Models (MLLMs) have gained significant attention across various domains. However, their widespread adoption has also raised serious safety concerns. In this paper, we uncover a new safety risk of MLLMs:…

Machine Learning · Computer Science 2025-09-17 Yifan Lan , Yuanpu Cao , Weitong Zhang , Lu Lin , Jinghui Chen

Existing adversarial attacks for VLP models are mostly sample-specific, resulting in substantial computational overhead when scaled to large datasets or new scenarios. To overcome this limitation, we propose Hierarchical Refinement Attack…

Computer Vision and Pattern Recognition · Computer Science 2026-02-18 Peng-Fei Zhang , Zi Huang

In-context learning (ICL) has emerged as a powerful paradigm leveraging LLMs for specific downstream tasks by utilizing labeled examples as demonstrations (demos) in the preconditioned prompts. Despite its promising performance, crafted…

Machine Learning · Computer Science 2025-05-30 Xiangyu Zhou , Yao Qiang , Saleh Zare Zade , Prashant Khanduri , Dongxiao Zhu

Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended outputs by introducing (small) perturbations to the inputs.…

Cryptography and Security · Computer Science 2024-01-22 Yunjie Ge , Qian Wang , Huayang Huang , Qi Li , Cong Wang , Chao Shen , Lingchen Zhao , Peipei Jiang , Zheng Fang , Shenyi Zhang

We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…

Cryptography and Security · Computer Science 2023-10-12 Erfan Shayegani , Yue Dong , Nael Abu-Ghazaleh

Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries.…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Zhiqiang Wang , Dongrui Liu , Yan Li , Zonghao Ying , Wei Xue , Wenhan Luo , Yike Guo
‹ Prev 1 2 3 10 Next ›