English
Related papers

Related papers: BSPA: Exploring Black-box Stealthy Prompt Attacks …

200 papers

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Kyle Stein , Andrew Arash Mahyari , Guillermo Francia , Eman El-Sheikh

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yangming Chen

With the rapid advancement of generative AI, users increasingly rely on image-generation models for image design and creation. To achieve faithful outputs, users typically engage in multi-turn interactions during image refinement: a…

Cryptography and Security · Computer Science 2026-05-12 Desen Sun , Jason Hon , Howe Wang , Saarth Rajan , Meng Xu , Sihang Liu

Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the models themselves…

Cryptography and Security · Computer Science 2026-01-09 Zhengyuan Jiang , Yuepeng Hu , Yuchen Yang , Yinzhi Cao , Neil Zhenqiang Gong

Text-conditioned image generation models have recently achieved astonishing image quality and alignment results. Consequently, they are employed in a fast-growing number of applications. Since they are highly data-driven, relying on…

Computer Vision and Pattern Recognition · Computer Science 2023-09-22 Manuel Brack , Patrick Schramowski , Kristian Kersting

This paper presents a novel approach to enhance image-to-image generation by leveraging the multimodal capabilities of the Large Language and Vision Assistant (LLaVA). We propose a framework where LLaVA analyzes input images and generates…

Computer Vision and Pattern Recognition · Computer Science 2024-11-13 Zhicheng Ding , Panfeng Li , Qikai Yang , Siyang Li

Large-scale vision-language models, especially CLIP, have demonstrated remarkable performance across diverse downstream tasks. Soft prompts, as carefully crafted modules that efficiently adapt vision-language models to specific tasks,…

Cryptography and Security · Computer Science 2026-05-27 Wenyuan Yang , Yichen Sun , Changzheng Chen , Zhixuan Chu , Jiaheng Zhang , Yiming Li , Dacheng Tao

Large Language Models remain vulnerable to adversarial prompts that elicit toxic content even after safety alignment. We present ToxSearch, a black-box evolutionary framework that tests model safety by evolving prompts in a synchronous…

Neural and Evolutionary Computing · Computer Science 2026-01-27 Onkar Shelar , Travis Desell

Text-to-image generative models have demonstrated remarkable capabilities in generating high-quality images based on textual prompts. However, crafting prompts that accurately capture the user's creative intent remains challenging. It often…

Human-Computer Interaction · Computer Science 2023-04-20 Stephen Brade , Bryan Wang , Mauricio Sousa , Sageev Oore , Tovi Grossman

Several years of research have shown that machine-learning systems are vulnerable to adversarial examples, both in theory and in practice. Until now, such attacks have primarily targeted visual models, exploiting the gap between human and…

Computation and Language · Computer Science 2021-12-14 Nicholas Boucher , Ilia Shumailov , Ross Anderson , Nicolas Papernot

Despite substantial progress in text-to-image generation, achieving precise text-image alignment remains challenging, particularly for prompts with rich compositional structure or imaginative elements. To address this, we introduce Negative…

Computer Vision and Pattern Recognition · Computer Science 2025-12-12 Sangha Park , Eunji Kim , Yeongtak Oh , Jooyoung Choi , Sungroh Yoon

Current large language models (LLMs) provide a strong foundation for large-scale user-oriented natural language tasks. A large number of users can easily inject adversarial text or instructions through the user interface, thus causing LLMs…

Cryptography and Security · Computer Science 2024-11-12 Chong Zhang , Mingyu Jin , Qinkai Yu , Chengzhi Liu , Haochen Xue , Xiaobo Jin

Federated Prompt Tuning (FPT) is an efficient method for cross-client collaborative fine-tuning of large Vision-Language Models (VLMs). However, models tuned using FPT are vulnerable to adversarial attacks, leading to misclassification in…

Computer Vision and Pattern Recognition · Computer Science 2025-09-10 Kun Zhai , Siheng Chen , Xingjun Ma , Yu-Gang Jiang

Diffusion models have been widely deployed in various image generation tasks, demonstrating an extraordinary connection between image and text modalities. Although prior studies have explored the vulnerability of diffusion models from the…

Machine Learning · Computer Science 2025-01-06 Dingcheng Yang , Yang Bai , Xiaojun Jia , Yang Liu , Xiaochun Cao , Wenjian Yu

Visual Generative AI models have demonstrated remarkable capability in generating high-quality images from user inputs like text prompts. However, because these models have billions of parameters, they risk memorizing certain parts of the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-18 Lena Reissinger , Yuanyuan Li , Anna-Carolina Haensch , Neeraj Sarna

The integration of large language models with external content has enabled applications such as Microsoft Copilot but also introduced vulnerabilities to indirect prompt injection attacks. In these attacks, malicious instructions embedded…

Computation and Language · Computer Science 2025-01-28 Jingwei Yi , Yueqi Xie , Bin Zhu , Emre Kiciman , Guangzhong Sun , Xing Xie , Fangzhao Wu

Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…

Machine Learning · Computer Science 2026-03-24 Guangnian Wan , Xinyin Ma , Gongfan Fang , Xinchao Wang

In recent years, there has been an explosive growth in multimodal learning. Image captioning, a classical multimodal task, has demonstrated promising applications and attracted extensive research attention. However, recent studies have…

Cryptography and Security · Computer Science 2024-06-11 Wenshu Fan , Hongwei Li , Wenbo Jiang , Meng Hao , Shui Yu , Xiao Zhang

Text-to-image (T2I) generative models such as Stable Diffusion and FLUX can synthesize realistic, high-quality images directly from textual prompts. The resulting image quality depends critically on well-crafted prompts that specify both…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Mingzhe Li , Renhao Zhang , Zhiyang Wen , Siqi Pan , Bruno Castro da Silva , Juan Zhai , Shiqing Ma

Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and…

Artificial Intelligence · Computer Science 2025-09-10 Minghui Li , Hao Zhang , Yechao Zhang , Wei Wan , Shengshan Hu , pei Xiaobing , Jing Wang