English
Related papers

Related papers: T2IShield: Defending Against Backdoors on Text-to-…

200 papers

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers. As various attack and defense models have been…

Machine Learning · Computer Science 2022-11-02 Ganqu Cui , Lifan Yuan , Bingxiang He , Yangyi Chen , Zhiyuan Liu , Maosong Sun

Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-to-image models may be tricked into generating…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 Xinfeng Li , Yuchen Yang , Jiangyi Deng , Chen Yan , Yanjiao Chen , Xiaoyu Ji , Wenyuan Xu

Self-supervised and multimodal vision encoders learn strong visual representations that are widely adopted in downstream vision tasks and large vision-language models (LVLMs). However, downstream users often rely on third-party pretrained…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Siquan Huang , Yijiang Li , Ningzhi Gao , Xingfu Yan , Leyu Shi , Ying Gao

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target…

Computer Vision and Pattern Recognition · Computer Science 2020-06-17 Shihao Zhao , Xingjun Ma , Xiang Zheng , James Bailey , Jingjing Chen , Yu-Gang Jiang

With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing…

Machine Learning · Computer Science 2024-07-02 Shangxi Wu , Qiuyang He , Jian Yu , Jitao Sang

This paper explores a novel lightweight approach LightFair to achieve fair text-to-image diffusion models (T2I DMs) by addressing the adverse effects of the text encoder. Most existing methods either couple different parts of the diffusion…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Boyu Han , Qianqian Xu , Shilong Bao , Zhiyong Yang , Kangli Zi , Qingming Huang

Deep neural networks have demonstrated remarkable success across numerous tasks, yet they remain vulnerable to Trojan (backdoor) attacks, raising serious concerns about their safety in real-world mission-critical applications. A common…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Hossein Mirzaei , Zeinab Taghavi , Sepehr Rezaee , Masoud Hadi , Moein Madadi , Mackenzie W. Mathis

Backdoor (Trojan) attack is a common threat to deep neural networks, where samples from one or more source classes embedded with a backdoor trigger will be misclassified to adversarial target classes. Existing methods for detecting whether…

Machine Learning · Computer Science 2023-11-17 Zhen Xiang , Zidi Xiong , Bo Li

Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two factors: lack of fine-grained spatial supervision in training…

Computer Vision and Pattern Recognition · Computer Science 2025-12-30 Sarah Rastegar , Violeta Chatalbasheva , Sieger Falkena , Anuj Singh , Yanbo Wang , Tejas Gokhale , Hamid Palangi , Hadi Jamali-Rad

Text-to-image (T2I) diffusion models lack an efficient mechanism for early quality assessment, leading to costly trial-and-error in multi-generation scenarios such as prompt iteration, agent-based generation, and flow-grpo. We reveal a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Benlei Cui , Bukun Huang , Zhizeng Ye , Xuemei Dong , Tuo Chen , Hui Xue , Dingkang Yang , Longtao Huang , Jingqun Tang , Haiwen Hong

We present a Multimodal Backdoor Defense technique TIJO (Trigger Inversion using Joint Optimization). Recent work arXiv:2112.07668 has demonstrated successful backdoor attacks on multimodal models for the Visual Question Answering task.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-09 Indranil Sur , Karan Sikka , Matthew Walmer , Kaushik Koneripalli , Anirban Roy , Xiao Lin , Ajay Divakaran , Susmit Jha

We propose a Universal Defence against backdoor attacks based on Clustering and Centroids Analysis (CCA-UD). The goal of the defence is to reveal whether a Deep Neural Network model is subject to a backdoor attack by inspecting the training…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Wei Guo , Benedetta Tondi , Mauro Barni

Deep learning-based lane detection (LD) plays a critical role in autonomous driving and advanced driver assistance systems. However, its vulnerability to backdoor attacks presents a significant security concern. Existing backdoor attack…

Cryptography and Security · Computer Science 2026-03-26 Yifan Liao , Yuxin Cao , Yedi Zhang , Wentao He , Yan Xiao , Xianglong Du , Zhiyong Huang , Jin Song Dong

Recent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation of Not Safe for Work (NSFW) content. Previous research has…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Yaopei Zeng , Yuanpu Cao , Bochuan Cao , Yurui Chang , Jinghui Chen , Lu Lin

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Xiaoxuan Han , Songlin Yang , Wei Wang , Yang Li , Jing Dong

Pervasive backdoors are triggered by dynamic and pervasive input perturbations. They can be intentionally injected by attackers or naturally exist in normally trained models. They have a different nature from the traditional static and…

Cryptography and Security · Computer Science 2022-06-22 Guanhong Tao , Yingqi Liu , Siyuan Cheng , Shengwei An , Zhuo Zhang , Qiuling Xu , Guangyu Shen , Xiangyu Zhang

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

Cryptography and Security · Computer Science 2022-10-20 Yangyi Chen , Fanchao Qi , Hongcheng Gao , Zhiyuan Liu , Maosong Sun

With the development of diffusion-based customization methods like DreamBooth, individuals now have access to train the models that can generate their personalized images. Despite the convenience, malicious users have misused these…

Computer Vision and Pattern Recognition · Computer Science 2024-07-29 Yisu Liu , Jinyang An , Wanqian Zhang , Dayan Wu , Jingzi Gu , Zheng Lin , Weiping Wang

Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…

Cryptography and Security · Computer Science 2024-12-03 Pengfei He , Yue Xing , Han Xu , Jie Ren , Yingqian Cui , Shenglai Zeng , Jiliang Tang , Makoto Yamada , Mohammad Sabokrou

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when a trigger is present. This survey reviews the rapidly…

Cryptography and Security · Computer Science 2025-09-10 Bilal Hussain Abbasi , Yanjun Zhang , Leo Zhang , Shang Gao