English
Related papers

Related papers: ChatGPT as an Attack Tool: Stealthy Textual Backdo…

200 papers

With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been…

Cryptography and Security · Computer Science 2019-06-05 Jiazhu Dai , Chuanshuai Chen

Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments. A malicious backdoor could be embedded in a model by poisoning the training dataset, whose intention is to make…

Cryptography and Security · Computer Science 2021-03-25 Yinpeng Dong , Xiao Yang , Zhijie Deng , Tianyu Pang , Zihao Xiao , Hang Su , Jun Zhu

Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated expressions to enhance the performance of LLMs. However,…

Cryptography and Security · Computer Science 2026-02-06 Zihan Wang , Hongwei Li , Rui Zhang , Wenbo Jiang , Guowen Xu

Over the past few years, the emergence of backdoor attacks has presented significant challenges to deep learning systems, allowing attackers to insert backdoors into neural networks. When data with a trigger is processed by a backdoor…

Cryptography and Security · Computer Science 2025-03-07 Haiyang Yu , Tian Xie , Jiaping Gui , Pengyang Wang , Ping Yi , Yue Wu

Recent advancement in large-scale Artificial Intelligence (AI) models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution (OoD) data as…

Cryptography and Security · Computer Science 2025-05-01 Jianbo Gao , Keke Gai , Jing Yu , Liehuang Zhu , Qi Wu

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…

Computation and Language · Computer Science 2022-04-28 Leilei Gan , Jiwei Li , Tianwei Zhang , Xiaoya Li , Yuxian Meng , Fei Wu , Yi Yang , Shangwei Guo , Chun Fan

Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the context of LLMs deployed as Web Services, which typically…

Computation and Language · Computer Science 2025-02-13 Wenjie Mo , Jiashu Xu , Qin Liu , Jiongxiao Wang , Jun Yan , Hadi Askari , Chaowei Xiao , Muhao Chen

Backdoor attacks in machine learning have drawn significant attention for their potential to compromise models stealthily, yet most research has focused on homogeneous data such as images. In this work, we propose a novel backdoor attack on…

Machine Learning · Computer Science 2025-11-11 Behrad Tajalli , Stefanos Koffas , Stjepan Picek

Diffusion models are powerful generative models in continuous data domains such as image and video data. Discrete graph diffusion models (DGDMs) have recently extended them for graph generation, which are crucial in fields like molecule and…

Cryptography and Security · Computer Science 2025-03-11 Jiawen Wang , Samin Karim , Yuan Hong , Binghui Wang

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious prompts that induce…

Computation and Language · Computer Science 2025-03-07 Honglin Mu , Han He , Yuxin Zhou , Yunlong Feng , Yang Xu , Libo Qin , Xiaoming Shi , Zeming Liu , Xudong Han , Qi Shi , Qingfu Zhu , Wanxiang Che

Text-to-image diffusion models can generate realistic images based on textual inputs, enabling users to convey their opinions visually through language. Meanwhile, within language, emotion plays a crucial role in expressing personal…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Tianyu Wei , Shanmin Pang , Qi Guo , Yizhuo Ma , Xiaofeng Cao , Qing Guo

Backdoor attacks pose a serious threat to deep learning models by allowing adversaries to implant hidden behaviors that remain dormant on clean inputs but are maliciously triggered at inference. Existing backdoor attack methods typically…

Cryptography and Security · Computer Science 2025-11-18 Lijie Hu , Junchi Liao , Weimin Lyu , Shaopeng Fu , Tianhao Huang , Shu Yang , Guimin Hu , Di Wang

Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural…

Cryptography and Security · Computer Science 2025-02-11 Yihe Zhou , Tao Ni , Wei-Bin Lee , Qingchuan Zhao

Machine learning (ML) has made tremendous progress during the past decade and is being adopted in various critical real-world applications. However, recent research has shown that ML models are vulnerable to multiple security and privacy…

Cryptography and Security · Computer Science 2022-03-07 Ahmed Salem , Rui Wen , Michael Backes , Shiqing Ma , Yang Zhang

Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…

Information Retrieval · Computer Science 2023-04-19 Jiawei Liu , Yangyang Kang , Di Tang , Kaisong Song , Changlong Sun , Xiaofeng Wang , Wei Lu , Xiaozhong Liu

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Cryptography and Security · Computer Science 2026-01-06 Eric Xue , Ruiyi Zhang , Pengtao Xie

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

Computation and Language · Computer Science 2023-01-26 Jiali Wei , Ming Fan , Wenjing Jiao , Wuxia Jin , Ting Liu

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers. These attacks, however, generally assume that the victim model is…

Computation and Language · Computer Science 2024-01-17 Tom Roth , Inigo Jauregi Unanue , Alsharif Abuadbba , Massimo Piccardi

Neural text detectors are models trained to detect whether a given text was generated by a language model or written by a human. In this paper, we investigate three simple and resource-efficient strategies (parameter tweaking, prompt…

Computation and Language · Computer Science 2023-11-06 Vitalii Fishchuk , Daniel Braun

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

Cryptography and Security · Computer Science 2026-03-18 Ruyi Zhang , Heng Gao , Songlei Jian , Yusong Tan , Haifang Zhou