English
Related papers

Related papers: Fine-mixing: Mitigating Backdoors in Fine-tuned La…

200 papers

Backdoor attacks represent one of the major threats to machine learning models. Various efforts have been made to mitigate backdoors. However, existing defenses have become increasingly complex and often require high computational resources…

Cryptography and Security · Computer Science 2022-12-20 Zeyang Sha , Xinlei He , Pascal Berrang , Mathias Humbert , Yang Zhang

Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the fine-tuning process…

Artificial Intelligence · Computer Science 2025-04-08 Hao Du , Shang Liu , Lele Zheng , Yang Cao , Atsuyoshi Nakamura , Lei Chen

Backdoor attack aims at inducing neural models to make incorrect predictions for poison data while keeping predictions on the clean dataset unchanged, which creates a considerable threat to current natural language processing (NLP) systems.…

Computation and Language · Computer Science 2023-03-28 Xukun Zhou , Jiwei Li , Tianwei Zhang , Lingjuan Lyu , Muqiao Yang , Jun He

The increasing use of large language models (LLMs) trained by third parties raises significant security concerns. In particular, malicious actors can introduce backdoors through poisoning attacks to generate undesirable outputs. While such…

Cryptography and Security · Computer Science 2024-07-19 Shuli Jiang , Swanand Ravindra Kadhe , Yi Zhou , Farhan Ahmed , Ling Cai , Nathalie Baracaldo

Large pre-trained language models (PLMs) have proven to be a crucial component of modern natural language processing systems. PLMs typically need to be fine-tuned on task-specific downstream datasets, which makes it hard to claim the…

Computation and Language · Computer Science 2023-02-13 Chenxi Gu , Chengsong Huang , Xiaoqing Zheng , Kai-Wei Chang , Cho-Jui Hsieh

Human language encompasses a wide range of intricate and diverse implicit features, which attackers can exploit to launch adversarial or backdoor attacks, compromising DNN models for NLP tasks. Existing model-oriented defenses often require…

Machine Learning · Computer Science 2025-09-26 Yi Jiang , Oubo Ma , Yong Yang , Tong Zhang , Shouling Ji

Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…

Computer Vision and Pattern Recognition · Computer Science 2024-05-21 Yangming Chen

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the…

Cryptography and Security · Computer Science 2025-10-07 Yulin Chen , Haoran Li , Yuan Sui , Yangqiu Song , Bryan Hooi

Existing research on training-time attacks for deep neural networks (DNNs), such as backdoors, largely assume that models are static once trained, and hidden backdoors trained into models remain active indefinitely. In practice, models are…

Cryptography and Security · Computer Science 2023-02-10 Huiying Li , Arjun Nitin Bhagoji , Yuxin Chen , Haitao Zheng , Ben Y. Zhao

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Cryptography and Security · Computer Science 2023-07-28 Nikhil Kandpal , Matthew Jagielski , Florian Tramèr , Nicholas Carlini

Recently, deep neural networks (DNNs) have been deployed in safety-critical systems such as autonomous vehicles and medical devices. Shortly after that, the vulnerability of DNNs were revealed by stealthy adversarial examples where crafted…

Cryptography and Security · Computer Science 2021-12-28 Behnam Ghavami , Seyd Movi , Zhenman Fang , Lesley Shannon

When machine learning training is outsourced to third parties, $backdoor$ $attacks$ become practical as the third party who trains the model may act maliciously to inject hidden behaviors into the otherwise accurate model. Until now, the…

Cryptography and Security · Computer Science 2022-11-16 Sanghyun Hong , Nicholas Carlini , Alexey Kurakin

Deep Neural Networks (DNNs) are vulnerable to adversarial examples generated by imposing subtle perturbations to inputs that lead a model to predict incorrect outputs. Currently, a large number of researches on defending adversarial…

Computer Vision and Pattern Recognition · Computer Science 2020-01-01 Hua Wang , Jie Wang , Zhaoxia Yin

Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor…

Cryptography and Security · Computer Science 2022-10-13 Haotao Wang , Junyuan Hong , Aston Zhang , Jiayu Zhou , Zhangyang Wang

One major goal of the AI security community is to securely and reliably produce and deploy deep learning models for real-world applications. To this end, data poisoning based backdoor attacks on deep neural networks (DNNs) in the production…

Cryptography and Security · Computer Science 2022-05-30 Xiangyu Qi , Tinghao Xie , Ruizhe Pan , Jifeng Zhu , Yong Yang , Kai Bu

Pre-trained language models (PLMs) have attracted enormous attention over the past few years with their unparalleled performances. Meanwhile, the soaring cost to train PLMs as well as their amazing generalizability have jointly contributed…

Computation and Language · Computer Science 2024-06-10 Tianrong Zhang , Zhaohan Xi , Ting Wang , Prasenjit Mitra , Jinghui Chen

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 have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes.…

Cryptography and Security · Computer Science 2023-10-30 Lu Yan , Zhuo Zhang , Guanhong Tao , Kaiyuan Zhang , Xuan Chen , Guangyu Shen , Xiangyu Zhang

Together with impressive advances touching every aspect of our society, AI technology based on Deep Neural Networks (DNN) is bringing increasing security concerns. While attacks operating at test time have monopolised the initial attention…

Cryptography and Security · Computer Science 2021-11-17 Wei Guo , Benedetta Tondi , Mauro Barni

Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activation anomaly analysis or trigger reverse engineering and often require clean samples or…

Cryptography and Security · Computer Science 2026-05-20 Yinbo Yu , Jing Fang , Xuewen Zhang , Chunwei Tian , Qi Zhu , Daoqiang Zhang , Jiajia Liu