English
Related papers

Related papers: Systematic Evaluation of Backdoor Data Poisoning A…

200 papers

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

Federated learning security research has predominantly focused on backdoor threats from a minority of malicious clients that intentionally corrupt model updates. This paper challenges this paradigm by investigating a more pervasive and…

Cryptography and Security · Computer Science 2026-02-18 Haodong Zhao , Jinming Hu , Gongshen Liu

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 attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorithm, e.g., by…

Machine Learning · Computer Science 2021-11-03 Kathrin Grosse , Taesung Lee , Battista Biggio , Youngja Park , Michael Backes , Ian Molloy

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

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 success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative…

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Computation and Language · Computer Science 2024-04-04 Jiashu Xu , Mingyu Derek Ma , Fei Wang , Chaowei Xiao , Muhao Chen

Code LLMs are increasingly employed in software development. However, studies have shown that they are vulnerable to backdoor attacks: when a trigger (a specific input pattern) appears in the input, the backdoor will be activated and cause…

Cryptography and Security · Computer Science 2025-10-07 Chenyu Wang , Zhou Yang , Yaniv Harel , David Lo

Deep neural networks (DNNs) are vulnerable to backdoor attacks which can hide backdoor triggers in DNNs by poisoning training data. A backdoored model behaves normally on clean test images, yet consistently predicts a particular target…

Computer Vision and Pattern Recognition · Computer Science 2020-06-17 Shihao Zhao , Xingjun Ma , Xiang Zheng , James Bailey , Jingjing Chen , Yu-Gang Jiang

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

Large-scale unlabeled data has spurred recent progress in self-supervised learning methods that learn rich visual representations. State-of-the-art self-supervised methods for learning representations from images (e.g., MoCo, BYOL, MSF) use…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Aniruddha Saha , Ajinkya Tejankar , Soroush Abbasi Koohpayegani , Hamed Pirsiavash

Federated learning allows multiple users to collaboratively train a shared classification model while preserving data privacy. This approach, where model updates are aggregated by a central server, was shown to be vulnerable to poisoning…

Machine Learning · Computer Science 2020-12-17 Chien-Lun Chen , Leana Golubchik , Marco Paolieri

Adversarial data poisoning is an effective attack against machine learning and threatens model integrity by introducing poisoned data into the training dataset. So far, it has been studied mostly for classification, even though regression…

Machine Learning · Computer Science 2020-09-16 Nicolas Michael Müller , Daniel Kowatsch , Konstantin Böttinger

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Cryptography and Security · Computer Science 2022-10-21 You Guo , Jun Wang , Trevor Cohn

We consider data poisoning attacks, a class of adversarial attacks on machine learning where an adversary has the power to alter a small fraction of the training data in order to make the trained classifier satisfy certain objectives. While…

Machine Learning · Computer Science 2018-08-29 Yizhen Wang , Kamalika Chaudhuri

While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to data poisoning attacks, but these studies placed stricter requirements…

Machine Learning · Computer Science 2024-06-18 Zhuoshi Pan , Yuguang Yao , Gaowen Liu , Bingquan Shen , H. Vicky Zhao , Ramana Rao Kompella , Sijia Liu

We propose a novel clustering mechanism based on an incompatibility property between subsets of data that emerges during model training. This mechanism partitions the dataset into subsets that generalize only to themselves, i.e., training…

Machine Learning · Computer Science 2023-04-28 Charles Jin , Melinda Sun , Martin Rinard

Recent studies revealed that deep neural networks (DNNs) are exposed to backdoor threats when training with third-party resources (such as training samples or backbones). The backdoored model has promising performance in predicting benign…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Chengxiao Luo , Yiming Li , Yong Jiang , Shu-Tao Xia

Semi-supervised learning methods can train high-accuracy machine learning models with a fraction of the labeled training samples required for traditional supervised learning. Such methods do not typically involve close review of the…

Machine Learning · Computer Science 2022-12-07 Marissa Connor , Vincent Emanuele