paper-with-me

홈 › Papers

Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models

2026-04-07 · Yiyang Zhang, Chaojian Yu, Ziming Hong, Yuanjie Shao, Qinmu Peng, Tongliang Liu, Xinge You arxiv

Multimodal pretrained models are vulnerable to backdoor attacks, yet most existing methods rely on visual or multimodal triggers, which are impractical since visually embedded triggers rarely occur in real-world data. To overcome this limitation, we propose a novel Text-Guided Backdoor (TGB) attack on multimodal pretrained models, where commonly occurring words in textual descriptions serve as backdoor triggers, significantly improving stealthiness and practicality. Furthermore, we introduce visual adversarial perturbations on poisoned samples to modulate the model's learning of textual triggers, enabling a controllable and adjustable TGB attack. Extensive experiments on downstream tasks built upon multimodal pretrained models, including Composed Image Retrieval (CIR) and Visual Question Answering (VQA), demonstrate that TGB achieves practicality and stealthiness with adjustable attack success rates across diverse realistic settings, revealing critical security vulnerabilities in multimodal pretrained models.

📄 PDF Abstract BibTeX arXiv:2604.05809

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Question AnsweringImage Retrieval

Similar Papers 제목 키워드 기반

Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing

2022-01-09 · Lingfeng Shen, Haiyun Jiang, Lemao Liu, Shuming Shi

It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm to mislead the models. The most threate…

Backdoor AttackText Classification

Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound

2023-07-17 · Hanbo Cai, Pengcheng Zhang, Hai Dong, Yan Xiao 외

Deep neural networks (DNNs) have been widely and successfully adopted and deployed in various applications of speech recognition. Recently, a few works revealed that these models are vulnerable to backdoor attacks, where…

Backdoor Attackspeech-recognitionSpeech Recognition

Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers

2022-06-10 · Nan Luo, Yuanzhang Li, Yajie Wang, Shangbo Wu 외

Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clea…

Backdoor Attackbackdoor defenseVocal Bursts Valence Prediction

TASER: Task-Aware Spectral Energy Refine for Backdoor Suppression in UAV Swarms Decentralized Federated Learning

2026-03-10 · Sizhe Huang, Shujie Yang arxiv

As backdoor attacks in UAV-based decentralized federated learning (DFL) grow increasingly stealthy and sophisticated, existing defenses have likewise escalated in complexity. Yet these defenses, which rely heavily on out…

Federated LearningOutlier Detection

Stealthy Backdoor Attack to Real-world Models in Android Apps

2025-01-02 · Jiali Wei, Ming Fan, Xicheng Zhang, Wenjing Jiao 외

Powered by their superior performance, deep neural networks (DNNs) have found widespread applications across various domains. Many deep learning (DL) models are now embedded in mobile apps, making them more accessible to…

Backdoor Attack