English
Related papers

Related papers: CLIBE: Detecting Dynamic Backdoors in Transformer-…

200 papers

Deep neural networks (DNNs) are susceptible to backdoor attacks, where malicious functionality is embedded to allow attackers to trigger incorrect classifications. Old-school backdoor attacks use strong trigger features that can easily be…

Cryptography and Security · Computer Science 2024-04-26 Huming Qiu , Junjie Sun , Mi Zhang , Xudong Pan , Min Yang

Deep neural networks (DNNs) are vulnerable to backdoor attacks. The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoors that can be activated by adversary-specified trigger…

Cryptography and Security · Computer Science 2023-03-07 Tong Xu , Yiming Li , Yong Jiang , Shu-Tao Xia

Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…

Computation and Language · Computer Science 2026-04-21 San Kim , Gary Geunbae Lee

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susceptibility of PLMs to backdoor attacks, wherein the…

Machine Learning · Computer Science 2023-10-31 Ruixiang Tang , Jiayi Yuan , Yiming Li , Zirui Liu , Rui Chen , Xia Hu

Large Language Models (LLMs) are widely integrated into interactive systems such as dialogue agents and task-oriented assistants. This growing ecosystem also raises supply-chain risks, where adversaries can distribute poisoned models that…

Cryptography and Security · Computer Science 2026-05-26 Yiyang Lu , Jinwen He , Yue Zhao , Kai Chen , Ruigang Liang , Cheng Hong , Yingjun Zhang

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

Cryptography and Security · Computer Science 2025-12-05 Bingyin Zhao , Yingjie Lao

Natural Language Processing (NLP) methods have been broadly applied to clinical tasks. Machine learning and deep learning approaches have been used to improve the performance of clinical NLP. However, these approaches require sufficiently…

Computation and Language · Computer Science 2023-10-05 Xiruo Ding , Zhecheng Sheng , Meliha Yetişgen , Serguei Pakhomov , Trevor Cohen

Deep neural networks (DNNs) have made tremendous progress in the past ten years and have been applied in various critical applications. However, recent studies have shown that deep neural networks are vulnerable to backdoor attacks. By…

Cryptography and Security · Computer Science 2023-05-19 Xinrui Liu , Yajie Wang , Yu-an Tan , Kefan Qiu , Yuanzhang Li

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…

Cryptography and Security · Computer Science 2022-02-17 Yiming Li , Yong Jiang , Zhifeng Li , Shu-Tao Xia

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Cryptography and Security · Computer Science 2023-12-15 Lukas Struppek , Martin B. Hentschel , Clifton Poth , Dominik Hintersdorf , Kristian Kersting

Backdoor attacks have been widely studied to hide the misclassification rules in the normal models, which are only activated when the model is aware of the specific inputs (i.e., the trigger). However, despite their success in the…

Artificial Intelligence · Computer Science 2022-01-19 Liang Chen , Qibiao Peng , Jintang Li , Yang Liu , Jiawei Chen , Yong Li , Zibin Zheng

This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers…

Machine Learning · Computer Science 2024-07-23 Sanyam Vyas , Chris Hicks , Vasilios Mavroudis

Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic manipulation, which limits stealthiness. In addition, Prior…

Computation and Language · Computer Science 2026-05-13 Ziyu Liu , Tao Li , Tianjie Ni , Xiaolong Lan , Wengang Ma , Tao Yang , Guohua Wang , Junjiang He

Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…

Machine Learning · Computer Science 2022-06-17 Mikel Bober-Irizar , Ilia Shumailov , Yiren Zhao , Robert Mullins , Nicolas Papernot

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

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Felix Hsieh , Huy H. Nguyen , AprilPyone MaungMaung , Dmitrii Usynin , Isao Echizen

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

Cryptography and Security · Computer Science 2026-02-17 Anudeep Das , Prach Chantasantitam , Gurjot Singh , Lipeng He , Mariia Ponomarenko , Florian Kerschbaum

Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few training samples. The attacked model behaves normally on benign…

Cryptography and Security · Computer Science 2022-02-09 Kunzhe Huang , Yiming Li , Baoyuan Wu , Zhan Qin , Kui Ren

Deep Neural Networks (DNNs) have shown great promise in various domains. However, vulnerabilities associated with DNN training, such as backdoor attacks, are a significant concern. These attacks involve the subtle insertion of triggers…

Cryptography and Security · Computer Science 2025-09-18 Bart Pleiter , Behrad Tajalli , Stefanos Koffas , Gorka Abad , Jing Xu , Martha Larson , Stjepan Picek

Recent advances in natural language processing and the increased use of large language models have exposed new security vulnerabilities, such as backdoor attacks. Previous backdoor attacks require input manipulation after model distribution…

Computation and Language · Computer Science 2024-09-26 Minkyoo Song , Hanna Kim , Jaehan Kim , Youngjin Jin , Seungwon Shin