English
Related papers

Related papers: Train in Vain: Functionality-Preserving Poisoning …

200 papers

Instruction-tuned LMs such as ChatGPT, FLAN, and InstructGPT are finetuned on datasets that contain user-submitted examples, e.g., FLAN aggregates numerous open-source datasets and OpenAI leverages examples submitted in the browser…

Computation and Language · Computer Science 2023-05-02 Alexander Wan , Eric Wallace , Sheng Shen , Dan Klein

Large language models (LLMs) have gained widespread adoption across diverse applications due to their impressive generative capabilities. Their plug-and-play nature enables both developers and end users to interact with these models through…

Cryptography and Security · Computer Science 2025-10-21 Zongze Li , Jiawei Guo , Haipeng Cai

Train-time data poisoning attacks threaten machine learning models by introducing adversarial examples during training, leading to misclassification. Current defense methods often reduce generalization performance, are attack-specific, and…

Machine Learning · Computer Science 2024-06-04 Sunay Bhat , Jeffrey Jiang , Omead Pooladzandi , Alexander Branch , Gregory Pottie

Early research into data poisoning attacks against Large Language Models (LLMs) demonstrated the ease with which backdoors could be injected. More recent LLMs add step-by-step reasoning, expanding the attack surface to include the…

Cryptography and Security · Computer Science 2025-09-09 Hanna Foerster , Ilia Shumailov , Yiren Zhao , Harsh Chaudhari , Jamie Hayes , Robert Mullins , Yarin Gal

Data poisoning is a type of adversarial attack on training data where an attacker manipulates a fraction of data to degrade the performance of machine learning model. Therefore, applications that rely on external data-sources for training…

Machine Learning · Computer Science 2021-04-28 Sanjay Seetharaman , Shubham Malaviya , Rosni KV , Manish Shukla , Sachin Lodha

We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An adversary first adds a few carefully crafted points to the…

Machine Learning · Computer Science 2024-08-02 Jimmy Z. Di , Jack Douglas , Jayadev Acharya , Gautam Kamath , Ayush Sekhari

Modern large language models (LLMs) exhibit critical vulnerabilities to poison pill attacks: localized data poisoning that alters specific factual knowledge while preserving overall model utility. We systematically demonstrate these attacks…

Cryptography and Security · Computer Science 2025-02-27 Peng Yifeng , Wu Zhizheng , Chen Chen

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

Text-to-visualization (text-to-vis) models for tabular data have become essential tools in the era of big data, enabling users to generate visualizations and make data-driven decisions through natural language queries (NLQs). Despite their…

Cryptography and Security · Computer Science 2026-03-11 Shuaimin Li , Chen Jason Zhang , Xuanang Chen , Anni Peng , Zhuoyue Wan , Yuanfeng Song , Shiwen Ni , Min Yang , Fei Hao , Raymond Chi-Wing Wong

Code generation large language models (LLMs) are increasingly integrated into modern software development workflows. Recent work has shown that these models are vulnerable to backdoor and poisoning attacks that induce the generation of…

Cryptography and Security · Computer Science 2026-03-19 Shenao Yan , Shimaa Ahmed , Shan Jin , Sunpreet S. Arora , Yiwei Cai , Yizhen Wang , Yuan Hong

Machine learning techniques have been widely applied to various applications. However, they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can disrupt the learning procedure by injecting a fraction of…

Cryptography and Security · Computer Science 2021-05-11 Jian Chen , Xuxin Zhang , Rui Zhang , Chen Wang , Ling Liu

Data poisoning considers an adversary that distorts the training set of machine learning algorithms for malicious purposes. In this work, we bring to light one conjecture regarding the fundamentals of data poisoning, which we call the…

Machine Learning · Computer Science 2022-10-20 Wenxiao Wang , Alexander Levine , Soheil Feizi

Deep learning models are often trained on distributed, web-scale datasets crawled from the internet. In this paper, we introduce two new dataset poisoning attacks that intentionally introduce malicious examples to a model's performance. Our…

Machine learning is susceptible to poisoning attacks, in which an attacker controls a small fraction of the training data and chooses that data with the goal of inducing some behavior unintended by the model developer in the trained model.…

Machine Learning · Computer Science 2023-11-21 Evan Rose , Fnu Suya , David Evans

Growing applications of large language models (LLMs) trained by a third party raise serious concerns on the security vulnerability of LLMs.It has been demonstrated that malicious actors can covertly exploit these vulnerabilities in LLMs…

Cryptography and Security · Computer Science 2023-12-11 Shuli Jiang , Swanand Ravindra Kadhe , Yi Zhou , Ling Cai , Nathalie Baracaldo

LLM agents have demonstrated remarkable performance across various applications, primarily due to their advanced capabilities in reasoning, utilizing external knowledge and tools, calling APIs, and executing actions to interact with…

Machine Learning · Computer Science 2024-07-18 Zhaorun Chen , Zhen Xiang , Chaowei Xiao , Dawn Song , Bo Li

Without direct access to the client's data, federated learning (FL) is well-known for its unique strength in data privacy protection among existing distributed machine learning techniques. However, its distributive and iterative nature…

Machine Learning · Computer Science 2026-04-14 Hanxi Guo , Hao Wang , Tao Song , Tianhang Zheng , Yang Hua , Haibing Guan , Xiangyu Zhang

We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out. We achieve this by modifying subliminal…

Cryptography and Security · Computer Science 2026-02-06 Andrew Draganov , Tolga H. Dur , Anandmayi Bhongade , Mary Phuong

Data poisoning is a training-time attack that undermines the trustworthiness of learned models. In a targeted data poisoning attack, an adversary manipulates the training dataset to alter the classification of a targeted test point. Given…

Machine Learning · Computer Science 2025-11-18 Nakshatra Gupta , Sumanth Prabhu , Supratik Chakraborty , R Venkatesh

We revisit the efficacy of several practical methods for approximate machine unlearning developed for large-scale deep learning. In addition to complying with data deletion requests, one often-cited potential application for unlearning…

Machine Learning · Computer Science 2026-01-16 Martin Pawelczyk , Jimmy Z. Di , Yiwei Lu , Gautam Kamath , Ayush Sekhari , Seth Neel