English
Related papers

Related papers: Buster: Implanting Semantic Backdoor into Text Enc…

200 papers

The expansion of large-scale text-to-image diffusion models has raised growing concerns about their potential to generate undesirable or harmful content, ranging from fabricated depictions of public figures to sexually explicit images. To…

Cryptography and Security · Computer Science 2025-05-01 Jonas Henry Grebe , Tobias Braun , Marcus Rohrbach , Anna Rohrbach

Text-to-image diffusion models have been demonstrated with undesired generation due to unfiltered large-scale training data, such as sexual images and copyrights, necessitating the erasure of undesired concepts. Most existing methods focus…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Zheling Meng , Bo Peng , Xiaochuan Jin , Yue Jiang , Wei Wang , Jing Dong , Tieniu Tan

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

Computation and Language · Computer Science 2021-09-23 Zichao Li , Dheeraj Mekala , Chengyu Dong , Jingbo Shang

Text-to-image (T2I) diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of these models can inadvertently led they to…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Die Chen , Zhiwen Li , Cen Chen , Xiaodan Li , Jinyan Ye

With advances in diffusion models, image generation has shown significant performance improvements. This raises concerns about the potential abuse of image generation, such as the creation of explicit or violent images, commonly referred to…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Junha Park , Jaehui Hwang , Ian Ryu , Hyungkeun Park , Jiyoon Kim , Jong-Seok Lee

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Huiqiang Chen , Tianqing Zhu , Linlin Wang , Xin Yu , Longxiang Gao , Wanlei Zhou

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Cryptography and Security · Computer Science 2024-12-30 A. Dilara Yavuz , M. Emre Gursoy

It has been proved that deep neural networks are facing a new threat called backdoor attacks, where the adversary can inject backdoors into the neural network model through poisoning the training dataset. When the input containing some…

Cryptography and Security · Computer Science 2021-03-16 Chuanshuai Chen , Jiazhu Dai

Diffusion Models (DMs) have achieved remarkable success in image generation, yet recent studies reveal their vulnerability to backdoor attacks, where adversaries manipulate outputs via covert triggers embedded in inputs. Existing defenses,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-08 Lei Zhang , Yu Pan , Bingrong Dai , Lin Wang

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller

Extremely large image generators offer significant transformative potential across diverse sectors. It allows users to design specific prompts to generate realistic images through some black-box APIs. However, some studies reveal that image…

Cryptography and Security · Computer Science 2024-02-26 Yu Tian , Xiao Yang , Yinpeng Dong , Heming Yang , Hang Su , Jun Zhu

Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Alloy Das , Sanket Biswas , Prasun Roy , Subhankar Ghosh , Umapada Pal , Michael Blumenstein , Josep Lladós , Saumik Bhattacharya

The generative AI revolution in recent years has been spurred by an expansion in compute power and data quantity, which together enable extensive pre-training of powerful text-to-image (T2I) models. With their greater capabilities to…

Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images. To mitigate risk, concept erasure methods are studied to facilitate the model to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Ruidong Chen , Honglin Guo , Lanjun Wang , Chenyu Zhang , Weizhi Nie , An-An Liu

Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, causing models to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Ashwath Vaithinathan Aravindan , Abha Jha , Matthew Salaway , Atharva Sandeep Bhide , Duygu Nur Yaldiz

Backdoor attacks are a kind of insidious security threat against machine learning models. After being injected with a backdoor in training, the victim model will produce adversary-specified outputs on the inputs embedded with predesigned…

Computation and Language · Computer Science 2021-06-04 Fanchao Qi , Mukai Li , Yangyi Chen , Zhengyan Zhang , Zhiyuan Liu , Yasheng Wang , Maosong Sun

The rise in popularity of text-to-image generative artificial intelligence (AI) has attracted widespread public interest. We demonstrate that this technology can be attacked to generate content that subtly manipulates its users. We propose…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Jordan Vice , Naveed Akhtar , Richard Hartley , Ajmal Mian

The attention-based encoder-decoder framework has recently achieved impressive results for scene text recognition, and many variants have emerged with improvements in recognition quality. However, it performs poorly on contextless texts…

Computer Vision and Pattern Recognition · Computer Science 2020-07-20 Xiaoyu Yue , Zhanghui Kuang , Chenhao Lin , Hongbin Sun , Wayne Zhang

Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and biased behavior. This, in turn, hampers their applicability…

Computer Vision and Pattern Recognition · Computer Science 2024-07-25 Samuele Poppi , Tobia Poppi , Federico Cocchi , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Despite the impressive capabilities of generating images, text-to-image diffusion models are susceptible to producing undesirable outputs such as NSFW content and copyrighted artworks. To address this issue, recent studies have focused on…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Tianyun Yang , Juan Cao , Chang Xu