English
Related papers

Related papers: MBTSAD: Mitigating Backdoors in Language Models Ba…

200 papers

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

This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Mingsheng Li , Lin Zhang , Mingzhen Zhu , Zilong Huang , Gang Yu , Jiayuan Fan , Tao Chen

By injecting a small number of poisoned samples into the training set, backdoor attacks aim to make the victim model produce designed outputs on any input injected with pre-designed backdoors. In order to achieve a high attack success rate…

Cryptography and Security · Computer Science 2024-07-23 Minlong Peng , Zidi Xiong , Quang H. Nguyen , Mingming Sun , Khoa D. Doan , Ping Li

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…

Machine Learning · Computer Science 2025-08-08 Wenjie Huo , Katinka Wolter

The releases of powerful open-weight large language models (LLMs) are often not accompanied by access to their full training data. Existing interpretability methods, particularly those based on activations, often require or assume…

Machine Learning · Computer Science 2026-04-22 Ziqian Zhong , Aditi Raghunathan

Graph Neural Networks (GNNs) have achieved remarkable performance through their message-passing mechanism. However, recent studies have highlighted the vulnerability of GNNs to backdoor attacks, which can lead the model to misclassify…

Machine Learning · Computer Science 2025-01-13 Jiale Zhang , Bosen Rao , Chengcheng Zhu , Xiaobing Sun , Qingming Li , Haibo Hu , Xiapu Luo , Qingqing Ye , Shouling Ji

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

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Cryptography and Security · Computer Science 2025-06-19 Wassim Bouaziz , Mathurin Videau , Nicolas Usunier , El-Mahdi El-Mhamdi

Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks--most notably backdoor attacks. Existing KD…

Cryptography and Security · Computer Science 2026-05-26 Shanmin Wang , Dongdong Zhao

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…

Computation and Language · Computer Science 2023-12-27 Xuan Sheng , Zhicheng Li , Zhaoyang Han , Xiangmao Chang , Piji Li

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

Fine-tuned Large Language Models (LLMs) are vulnerable to backdoor attacks through data poisoning, yet the internal mechanisms governing these attacks remain a black box. Previous research on interpretability for LLM safety tends to focus…

Cryptography and Security · Computer Science 2025-10-01 Miao Yu , Zhenhong Zhou , Moayad Aloqaily , Kun Wang , Biwei Huang , Stephen Wang , Yueming Jin , Qingsong Wen

Self-Supervised Learning (SSL) has become a prominent paradigm for pre-training encoders to learning general-purpose representations from unlabeled data and releasing them on third-party platforms for broad downstream deep learning tasks.…

Machine Learning · Computer Science 2026-02-02 TIngxu Han , Wei Song , Weisong Sun , Ziqi Ding , Yebo Feng , Chunrong Fang , Jun Li , Hanwei Qian , Zhenyu Chen , Yang Liu

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Zhifang Zhang , Bojun Yang , Shuo He , Weitong Chen , Wei Emma Zhang , Olaf Maennel , Lei Feng , Miao Xu

Knowledge distillation has become a cornerstone in modern machine learning systems, celebrated for its ability to transfer knowledge from a large, complex teacher model to a more efficient student model. Traditionally, this process is…

Cryptography and Security · Computer Science 2026-01-13 Chen Wu , Qian Ma , Prasenjit Mitra , Sencun Zhu

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Cryptography and Security · Computer Science 2025-01-07 Shuai Zhao , Meihuizi Jia , Zhongliang Guo , Leilei Gan , Xiaoyu Xu , Xiaobao Wu , Jie Fu , Yichao Feng , Fengjun Pan , Luu Anh Tuan

Data-poisoning based backdoor attacks aim to insert backdoor into models by manipulating training datasets without controlling the training process of the target model. Existing attack methods mainly focus on designing triggers or fusion…

Cryptography and Security · Computer Science 2023-07-17 Zihao Zhu , Mingda Zhang , Shaokui Wei , Li Shen , Yanbo Fan , Baoyuan Wu

Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…

Cryptography and Security · Computer Science 2024-03-13 Hongwei Zhang , Xiaoyin Xu , Dongsheng An , Xianfeng Gu , Min Zhang

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Machine Learning · Computer Science 2023-10-31 Wencong You , Zayd Hammoudeh , Daniel Lowd

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Computation and Language · Computer Science 2021-11-02 Lujia Shen , Shouling Ji , Xuhong Zhang , Jinfeng Li , Jing Chen , Jie Shi , Chengfang Fang , Jianwei Yin , Ting Wang