English
Related papers

Related papers: GREAT: Generalizable Backdoor Attacks in RLHF via …

200 papers

Retrieval-augmented generation (RAG) enhances factual grounding by integrating retrieval mechanisms with generative models but introduces new attack surfaces, particularly through backdoor attacks. While prior research has largely focused…

Information Retrieval · Computer Science 2025-09-29 Gaurav Bagwe , Saket S. Chaturvedi , Xiaolong Ma , Xiaoyong Yuan , Kuang-Ching Wang , Lan Zhang

This paper presents GReAT (Graph Regularized Adversarial Training), a novel regularization method designed to enhance the robust classification performance of deep learning models. Adversarial examples, characterized by subtle perturbations…

Machine Learning · Computer Science 2024-05-06 Samet Bayram , Kenneth Barner

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Artificial Intelligence · Computer Science 2025-05-20 Yige Li , Hanxun Huang , Yunhan Zhao , Xingjun Ma , Jun Sun

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

Backdoor attack is a powerful attack algorithm to deep learning model. Recently, GNN's vulnerability to backdoor attack has been proved especially on graph classification task. In this paper, we propose the first backdoor detection and…

Artificial Intelligence · Computer Science 2022-09-08 Bingchen Jiang , Zhao Li

Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research. Training generative adversarial neural networks (GAN) usually requires large amounts of training…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Ruinan Jin , Xiaoxiao Li

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 vulnerabilities to backdoor attacks have recently threatened the trustworthiness of machine learning models in practical applications. Conventional wisdom suggests that not everyone can be an attacker since the process of designing the…

Cryptography and Security · Computer Science 2023-09-06 Sze Jue Yang , Quang Nguyen , Chee Seng Chan , Khoa D. Doan

The generalization bound is a crucial theoretical tool for assessing the generalizability of learning methods and there exist vast literatures on generalizability of normal learning, adversarial learning, and data poisoning. Unlike other…

Machine Learning · Computer Science 2024-06-05 Lijia Yu , Shuang Liu , Yibo Miao , Xiao-Shan Gao , Lijun Zhang

Recently, ChatGPT has gained significant attention in research due to its ability to interact with humans effectively. The core idea behind this model is reinforcement learning (RL) fine-tuning, a new paradigm that allows language models to…

Cryptography and Security · Computer Science 2023-04-25 Jiawen Shi , Yixin Liu , Pan Zhou , Lichao Sun

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications, e.g., medical question-answering, mathematical sciences, and code generation. However, they also exhibit inherent limitations, such…

Cryptography and Security · Computer Science 2025-06-23 Yang Jiao , Xiaodong Wang , Kai Yang

The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks,…

Cryptography and Security · Computer Science 2024-10-01 Qin Liu , Wenjie Mo , Terry Tong , Jiashu Xu , Fei Wang , Chaowei Xiao , Muhao Chen

With rapid advances, generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' inherent vulnerabilities may be exacerbated due to increased…

Cryptography and Security · Computer Science 2024-12-17 Haoran Li , Yulin Chen , Zihao Zheng , Qi Hu , Chunkit Chan , Heshan Liu , Yangqiu Song

Fine-tuning Large Language Models with untrusted data exposes models to backdoor attacks, where poisoned samples cause targeted misbehavior. Existing sample-filtering defenses rely on clustering, which requires sufficient data and can fail…

Cryptography and Security · Computer Science 2026-05-27 Haodong Zhao , Tianyi Xu , Tianhang Zhao , Zhuosheng Zhang , Gongshen Liu

Large language models (LLMs) have demonstrated superior performance compared to previous methods on various tasks, and often serve as the foundation models for many researches and services. However, the untrustworthy third-party LLMs may…

Cryptography and Security · Computer Science 2024-04-02 Hai Huang , Zhengyu Zhao , Michael Backes , Yun Shen , Yang Zhang

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

Speech recognition is an essential start ring of human-computer interaction, and recently, deep learning models have achieved excellent success in this task. However, when the model training and private data provider are always separated,…

Sound · Computer Science 2024-10-21 Wenhan Yao , Jiangkun Yang , Yongqiang He , Jia Liu , Weiping Wen

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where…

Computation and Language · Computer Science 2024-11-28 Chen Chen , Yuchen Sun , Xueluan Gong , Jiaxin Gao , Kwok-Yan Lam

Deep neural networks have significantly improved the performance of face forgery detection models in discriminating Artificial Intelligent Generated Content (AIGC). However, their security is significantly threatened by the injection of…

Computer Vision and Pattern Recognition · Computer Science 2024-01-02 Xiaoxuan Han , Songlin Yang , Wei Wang , Ziwen He , Jing Dong

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already…

Machine Learning · Computer Science 2021-07-14 Jing Xu , Minhui , Xue , Stjepan Picek