English
Related papers

Related papers: CBV: Clean-label Backdoor Attacks on Vision Langua…

200 papers

Multimodal large language models (MLLMs) face safety misalignment, where visual inputs enable harmful outputs. To address this, existing methods require explicit safety labels or contrastive data; yet, threat-related concepts are concrete…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Qishun Yang , Shu Yang , Lijie Hu , Di Wang

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…

Cryptography and Security · Computer Science 2024-04-02 Hai Huang , Zhengyu Zhao , Michael Backes , Yun Shen , Yang Zhang

With the significant development of large models in recent years, Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a wide range of multimodal understanding and reasoning tasks. Compared to traditional…

Computer Vision and Pattern Recognition · Computer Science 2024-07-15 Daizong Liu , Mingyu Yang , Xiaoye Qu , Pan Zhou , Yu Cheng , Wei Hu

Vision-language models (VLMs) seamlessly integrate visual and textual data to perform tasks such as image classification, caption generation, and visual question answering. However, adversarial images often struggle to deceive all prompts…

Multimedia · Computer Science 2024-06-21 Xikang Yang , Xuehai Tang , Fuqing Zhu , Jizhong Han , Songlin Hu

We propose VIBE, a model-agnostic framework that trains classifiers resilient to backdoor attacks. The key concept behind our approach is to treat malicious inputs and corrupted labels from the training dataset as observed random variables,…

Machine Learning · Computer Science 2025-08-27 Ivan Sabolić , Matej Grcić , Siniša Šegvić

Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. Currently, post-training backdoor…

Cryptography and Security · Computer Science 2024-10-22 Yanghao Su , Jie Zhang , Ting Xu , Tianwei Zhang , Weiming Zhang , Nenghai Yu

Vision-language models (VLMs) have revolutionized multimodal AI applications but introduce novel security vulnerabilities that remain largely unexplored. We present the first comprehensive study of steganographic prompt injection attacks…

Cryptography and Security · Computer Science 2025-07-31 Chetan Pathade

Recent advances in large vision-language models (VLMs) have demonstrated remarkable success across a wide range of visual understanding tasks. However, the robustness of these models against jailbreak attacks remains an open challenge. In…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Xiangyu Yin , Jiaxu Liu , Zhen Chen , Jinwei Hu , Yi Dong , Xiaowei Huang , Wenjie Ruan

Visual Question Answering (VQA) models, which fall under the category of vision-language models, conventionally execute multiple downsampling processes on image inputs to strike a balance between computational efficiency and model…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Xirui Zhou , Lianlei Shan , Xiaolin Gui

The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a popular class of…

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

Machine Learning · Computer Science 2025-02-11 Brian Formento , Chuan Sheng Foo , See-Kiong Ng

The proliferation of deepfake faces poses huge potential negative impacts on our daily lives. Despite substantial advancements in deepfake detection over these years, the generalizability of existing methods against forgeries from unseen…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Kaiqing Lin , Yuzhen Lin , Weixiang Li , Taiping Yao , Bin Li

Vision Large Language Models (VLLMs) are increasingly deployed to offer advanced capabilities on inputs comprising both text and images. While prior research has shown that adversarial attacks can transfer from open-source to proprietary…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Kai Hu , Weichen Yu , Li Zhang , Alexander Robey , Andy Zou , Chengming Xu , Haoqi Hu , Matt Fredrikson

How to evaluate large language models (LLMs) cleanly has been established as an important research era to genuinely report the performance of possibly contaminated LLMs. Yet, how to cleanly evaluate the visual language models (VLMs) is an…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Hongyuan Lu , Shujie Miao , Wai Lam

Despite the remarkable progress of diffusion models in image generation, recent studies reveal their vulnerability to backdoor attacks via covert visual or textual triggers. Although evolving defense mechanisms can detect most existing…

Cryptography and Security · Computer Science 2026-05-29 Jia Wu , Yu Pan , Junjun Yang , Yi Du

Large language models (LLMs) have demonstrated that large-scale pretraining enables systems to adapt rapidly to new problems with little supervision in the language domain. This success, however, has not translated as effectively to the…

Computer Vision and Pattern Recognition · Computer Science 2025-11-04 Pablo Acuaviva , Aram Davtyan , Mariam Hassan , Sebastian Stapf , Ahmad Rahimi , Alexandre Alahi , Paolo Favaro

There has been an increasing interest in the alignment of large language models (LLMs) with human values. However, the safety issues of their integration with a vision module, or vision language models (VLMs), remain relatively…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Xijia Tao , Shuai Zhong , Lei Li , Qi Liu , Lingpeng Kong

Vision-Language Models (VLMs) have shown solid ability for multimodal understanding of both visual and language contexts. However, existing VLMs often face severe challenges of hallucinations, meaning that VLMs tend to generate responses…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Jinjin Cao , Zhiyang Chen , Zijun Wang , Liyuan Ma , Weijian Luo , Guojun Qi

Current vision large language models (VLLMs) exhibit remarkable capabilities yet are prone to generate harmful content and are vulnerable to even the simplest jailbreaking attacks. Our initial analysis finds that this is due to the presence…

Machine Learning · Computer Science 2024-06-19 Yongshuo Zong , Ondrej Bohdal , Tingyang Yu , Yongxin Yang , Timothy Hospedales

Deep neural networks (DNNs) are vulnerable to a class of attacks called "backdoor attacks", which create an association between a backdoor trigger and a target label the attacker is interested in exploiting. A backdoored DNN performs well…

Computer Vision and Pattern Recognition · Computer Science 2023-01-23 Hasan Abed Al Kader Hammoud , Shuming Liu , Mohammed Alkhrashi , Fahad AlBalawi , Bernard Ghanem
‹ Prev 1 4 5 6 7 8 10 Next ›