English
Related papers

Related papers: The Hammer and the Nut: Is Bilevel Optimization Re…

200 papers

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

Machine Learning · Computer Science 2024-08-27 Alina Ermilova , Elizaveta Kovtun , Dmitry Berestnev , Alexey Zaytsev

To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{any} order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential…

Machine Learning · Computer Science 2022-08-30 Anshuka Rangi , Haifeng Xu , Long Tran-Thanh , Massimo Franceschetti

Data poisoning considers cases when an adversary manipulates the behavior of machine learning algorithms through malicious training data. Existing threat models of data poisoning center around a single metric, the number of poisoned…

Machine Learning · Computer Science 2023-12-08 Wenxiao Wang , Soheil Feizi

In this paper, we investigate how to manipulate the coefficients obtained via linear regression by adding carefully designed poisoning data points to the dataset or modify the original data points. Given the energy budget, we first provide…

Signal Processing · Electrical Eng. & Systems 2021-11-03 Fuwei Li , Lifeng Lai , Shuguang Cui

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-tuning on poisoned data, even when safeguarded by moderation…

Cryptography and Security · Computer Science 2025-07-18 Dillon Bowen , Brendan Murphy , Will Cai , David Khachaturov , Adam Gleave , Kellin Pelrine

Data poisoning aims to compromise a machine learning based software component by contaminating its training set to change its prediction results for test inputs. Existing methods for deciding data-poisoning robustness have either poor…

Software Engineering · Computer Science 2023-07-18 Yannan Li , Jingbo Wang , Chao Wang

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…

Cryptography and Security · Computer Science 2025-06-09 Tingchen Fu , Mrinank Sharma , Philip Torr , Shay B. Cohen , David Krueger , Fazl Barez

We study indiscriminate poisoning for linear learners where an adversary injects a few crafted examples into the training data with the goal of forcing the induced model to incur higher test error. Inspired by the observation that linear…

Machine Learning · Computer Science 2023-11-13 Fnu Suya , Xiao Zhang , Yuan Tian , David Evans

Recent research has highlighted the vulnerability of Deep Neural Networks (DNNs) against data poisoning attacks. These attacks aim to inject poisoning samples into the models' training dataset such that the trained models have inference…

Cryptography and Security · Computer Science 2025-06-03 Pengfei He , Han Xu , Jie Ren , Yingqian Cui , Hui Liu , Charu C. Aggarwal , Jiliang Tang

We show that by controlling parts of a physical environment in which a pre-trained deep neural network (DNN) is being fine-tuned online, an adversary can launch subtle data poisoning attacks that degrade the performance of the system. While…

Machine Learning · Computer Science 2020-12-08 Naman Patel , Prashanth Krishnamurthy , Siddharth Garg , Farshad Khorrami

Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…

Cryptography and Security · Computer Science 2023-06-06 Ziqing Yang , Xinlei He , Zheng Li , Michael Backes , Mathias Humbert , Pascal Berrang , Yang Zhang

This paper advances the understanding of how the size of a machine learning model affects its vulnerability to poisoning, despite state-of-the-art defenses. Given isotropic random honest feature vectors and the geometric median (or clipped…

Machine Learning · Computer Science 2024-09-27 Lê-Nguyên Hoang

This work introduces a verification framework that provides both sound and complete guarantees for data poisoning attacks during neural network training. We formulate adversarial data manipulation, model training, and test-time evaluation…

Machine Learning · Computer Science 2026-02-20 Philip Sosnin , Jodie Knapp , Fraser Kennedy , Josh Collyer , Calvin Tsay

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor…

Cryptography and Security · Computer Science 2023-06-05 Giorgio Severi , Simona Boboila , Alina Oprea , John Holodnak , Kendra Kratkiewicz , Jason Matterer

AI-based code generators have gained a fundamental role in assisting developers in writing software starting from natural language (NL). However, since these large language models are trained on massive volumes of data collected from…

Cryptography and Security · Computer Science 2024-03-12 Cristina Improta

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 study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find…

Machine Learning · Computer Science 2020-11-24 Amin Rakhsha , Goran Radanovic , Rati Devidze , Xiaojin Zhu , Adish Singla

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

This paper proposes an online environment poisoning algorithm tailored for reinforcement learning agents operating in a black-box setting, where an adversary deliberately manipulates training data to lead the agent toward a mischievous…

Machine Learning · Computer Science 2024-12-03 Jianhui Li , Bokang Zhang , Junfeng Wu

Neural network classifiers are vulnerable to data poisoning attacks, as attackers can degrade or even manipulate their predictions thorough poisoning only a few training samples. However, the robustness of heuristic defenses is hard to…

Machine Learning · Computer Science 2020-10-14 Ruoxin Chen , Jie Li , Chentao Wu , Bin Sheng , Ping Li