English
Related papers

Related papers: A Linear Approach to Data Poisoning

200 papers

Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the…

Machine Learning · Computer Science 2022-03-09 Maria-Florina Balcan , Avrim Blum , Steve Hanneke , Dravyansh Sharma

Minimizing risk with fairness constraints is one of the popular approaches to learning a fair classifier. Recent works showed that this approach yields an unfair classifier if the training set is corrupted. In this work, we study the…

Machine Learning · Computer Science 2022-05-10 Changhun Jo , Jy-yong Sohn , Kangwook Lee

Backdoor attacks impose a new threat in Deep Neural Networks (DNNs), where a backdoor is inserted into the neural network by poisoning the training dataset, misclassifying inputs that contain the adversary trigger. The major challenge for…

Machine Learning · Computer Science 2024-09-26 Yue Wang , Wenqing Li , Esha Sarkar , Muhammad Shafique , Michail Maniatakos , Saif Eddin Jabari

Modern machine learning increasingly requires training on a large collection of data from multiple sources, not all of which can be trusted. A particularly concerning scenario is when a small fraction of poisoned data changes the behavior…

Machine Learning · Computer Science 2021-04-26 Jonathan Hayase , Weihao Kong , Raghav Somani , Sewoong Oh

With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the…

Cryptography and Security · Computer Science 2021-05-20 Jialin Wen , Benjamin Zi Hao Zhao , Minhui Xue , Alina Oprea , Haifeng Qian

Stealthy data poisoning during fine-tuning can backdoor large language models (LLMs), threatening downstream safety. Existing detectors either use classifier-style probability signals--ill-suited to generation--or rely on rewriting, which…

Computation and Language · Computer Science 2025-11-13 Jinwen Chen , Hainan Zhang , Fei Sun , Qinnan Zhang , Sijia Wen , Ziwei Wang , Zhiming Zheng

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

Machine Learning · Computer Science 2024-09-05 Ivan Sabolić , Ivan Grubišić , Siniša Šegvić

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…

Machine Learning · Computer Science 2025-09-29 Sujeevan Aseervatham , Achraf Kerzazi , Younès Bennani

Deep neural network (DNN) classifiers are vulnerable to backdoor attacks. An adversary poisons some of the training data in such attacks by installing a trigger. The goal is to make the trained DNN output the attacker's desired class…

Machine Learning · Computer Science 2022-10-14 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Alvi Md Ishmam , Christopher Thomas

Training pipelines for machine learning (ML) based malware classification often rely on crowdsourced threat feeds, exposing a natural attack injection point. In this paper, we study the susceptibility of feature-based ML malware classifiers…

Cryptography and Security · Computer Science 2021-01-12 Giorgio Severi , Jim Meyer , Scott Coull , Alina Oprea

Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigger-carrying inputs to an attacker-chosen target class.…

Cryptography and Security · Computer Science 2026-05-05 Yi Yang , Jinyang Huang , Binbin Liu , Feng-Qi Cui , Xiaokang Zhou , Zhi Liu , Jie Zhang , Meng Li

Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a…

Machine Learning · Computer Science 2020-08-14 Neehar Peri , Neal Gupta , W. Ronny Huang , Liam Fowl , Chen Zhu , Soheil Feizi , Tom Goldstein , John P. Dickerson

Backdoor attacks involve the injection of a limited quantity of poisoned examples containing triggers into the training dataset. During the inference stage, backdoor attacks can uphold a high level of accuracy for normal examples, yet when…

Cryptography and Security · Computer Science 2024-06-25 Hanfeng Xia , Haibo Hong , Ruili Wang

We study data poisoning attacks in the online setting where training items arrive sequentially, and the attacker may perturb the current item to manipulate online learning. Importantly, the attacker has no knowledge of future training items…

Machine Learning · Computer Science 2019-06-03 Xuezhou Zhang , Xiaojin Zhu , Laurent Lessard

Data-driven techniques are used in cyber-physical systems (CPS) for controlling autonomous vehicles, handling demand responses for energy management, and modeling human physiology for medical devices. These data-driven techniques extract…

Machine Learning · Computer Science 2017-08-16 Sangdon Park , James Weimer , Insup Lee

Modern neural networks are often trained on massive datasets that are web scraped with minimal human inspection. As a result of this insecure curation pipeline, an adversary can poison or backdoor the resulting model by uploading malicious…

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

Recently, various parameter-efficient fine-tuning (PEFT) strategies for application to language models have been proposed and successfully implemented. However, this raises the question of whether PEFT, which only updates a limited set of…

Cryptography and Security · Computer Science 2024-04-01 Shuai Zhao , Leilei Gan , Luu Anh Tuan , Jie Fu , Lingjuan Lyu , Meihuizi Jia , Jinming Wen

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Cryptography and Security · Computer Science 2024-12-30 A. Dilara Yavuz , M. Emre Gursoy