English
Related papers

Related papers: Architectural Neural Backdoors from First Principl…

200 papers

Machine learning models are routinely deployed on a wide range of computing hardware. Although such hardware is typically expected to produce identical results, differences in its design can lead to small numerical variations during…

Machine Learning · Computer Science 2026-02-03 Jonas Möller , Erik Imgrund , Thorsten Eisenhofer , Konrad Rieck

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…

Computation and Language · Computer Science 2026-05-14 Liang Lin , Miao Yu , Moayad Aloqaily , Zhenhong Zhou , Kun Wang , Linsey Pang , Prakhar Mehrotra , Qingsong Wen

Graph Neural Networks (GNNs) have significantly advanced various downstream graph-relevant tasks, encompassing recommender systems, molecular structure prediction, social media analysis, etc. Despite the boosts of GNN, recent research has…

Machine Learning · Computer Science 2025-01-08 Xiao Yang , Gaolei Li , Jianhua Li

Backdoor attacks are among the most effective, practical, and stealthy attacks in deep learning. In this paper, we consider a practical scenario where a developer obtains a deep model from a third party and uses it as part of a…

Cryptography and Security · Computer Science 2025-03-28 Dorde Popovic , Amin Sadeghi , Ting Yu , Sanjay Chawla , Issa Khalil

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Machine Learning · Computer Science 2020-10-16 Zhen Xiang , David J. Miller , George Kesidis

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

Computation and Language · Computer Science 2021-03-30 Wenkai Yang , Lei Li , Zhiyuan Zhang , Xuancheng Ren , Xu Sun , Bin He

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

Backdoor attacks pose an important security threat to textual large language models. Exploring textual backdoor attacks not only helps reveal the potential security risks of models, but also promotes innovation and development of defense…

Cryptography and Security · Computer Science 2025-07-21 Yang Hou , Qiuling Yue , Lujia Chai , Guozhao Liao , Wenbao Han , Wei Ou

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

The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (DNN) models. Trigger inversion is an effective way of…

Machine Learning · Computer Science 2023-04-07 Zhenting Wang , Kai Mei , Juan Zhai , Shiqing Ma

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

Backdoor attack injects malicious behavior to models such that inputs embedded with triggers are misclassified to a target label desired by the attacker. However, natural features may behave like triggers, causing misclassification once…

Machine Learning · Computer Science 2021-03-18 Yingqi Liu , Guangyu Shen , Guanhong Tao , Zhenting Wang , Shiqing Ma , Xiangyu Zhang

Backdoor injection attack is an emerging threat to the security of neural networks, however, there still exist limited effective defense methods against the attack. In this paper, we propose BAERASE, a novel method that can erase the…

Cryptography and Security · Computer Science 2022-01-25 Yang Liu , Mingyuan Fan , Cen Chen , Ximeng Liu , Zhuo Ma , Li Wang , Jianfeng Ma

Deep learning (DL) compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified…

Cryptography and Security · Computer Science 2025-10-28 Simin Chen , Jinjun Peng , Yixin He , Junfeng Yang , Baishakhi Ray

This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for…

Machine Learning · Computer Science 2024-05-24 Peter Bajcsy , Maxime Bros

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

Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. A victim classifier will predict to an attacker-desired target class whenever a test sample is embedded with the same backdoor pattern (BP) that was used to…

Cryptography and Security · Computer Science 2022-03-15 Zhen Xiang , David J. Miller , George Kesidis

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

Recently, advanced NLP models have seen a surge in the usage of various applications. This raises the security threats of the released models. In addition to the clean models' unintentional weaknesses, {\em i.e.,} adversarial attacks, the…

Computation and Language · Computer Science 2021-01-18 Lichao Sun

The tremendous progress of autoencoders and generative adversarial networks (GANs) has led to their application to multiple critical tasks, such as fraud detection and sanitized data generation. This increasing adoption has fostered the…

Cryptography and Security · Computer Science 2020-10-09 Ahmed Salem , Yannick Sautter , Michael Backes , Mathias Humbert , Yang Zhang