English
Related papers

Related papers: The poison of dimensionality

200 papers

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

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…

Software Engineering · Computer Science 2024-05-21 Aftab Hussain , Md Rafiqul Islam Rabin , Mohammad Amin Alipour

Indiscriminate data poisoning attacks aim to decrease a model's test accuracy by injecting a small amount of corrupted training data. Despite significant interest, existing attacks remain relatively ineffective against modern machine…

Machine Learning · Computer Science 2023-06-07 Yiwei Lu , Gautam Kamath , Yaoliang Yu

Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process. Prior works focus on either availability attacks (i.e.,…

Machine Learning · Computer Science 2021-10-13 Bingyin Zhao , Yingjie Lao

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

Cryptography and Security · Computer Science 2022-10-07 Florian Tramèr , Reza Shokri , Ayrton San Joaquin , Hoang Le , Matthew Jagielski , Sanghyun Hong , Nicholas Carlini

Backdoor poisoning attacks are a threat to machine learning models trained on large data collected from untrusted sources; these attacks enable attackers to inject malicious behavior into the model that can be triggered by specially crafted…

Machine Learning · Computer Science 2026-01-06 Thorsten Peinemann , Paula Arnold , Sebastian Berndt , Thomas Eisenbarth , Esfandiar Mohammadi

Adversarial training instances can severely distort a model's behavior. This work investigates certified regression defenses, which provide guaranteed limits on how much a regressor's prediction may change under a poisoning attack. Our key…

Machine Learning · Computer Science 2023-01-02 Zayd Hammoudeh , Daniel Lowd

Data Poisoning attacks modify training data to maliciously control a model trained on such data. In this work, we focus on targeted poisoning attacks which cause a reclassification of an unmodified test image and as such breach model…

Computer Vision and Pattern Recognition · Computer Science 2021-05-11 Jonas Geiping , Liam Fowl , W. Ronny Huang , Wojciech Czaja , Gavin Taylor , Michael Moeller , Tom Goldstein

Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and…

Cryptography and Security · Computer Science 2024-10-18 Yiming Zhang , Javier Rando , Ivan Evtimov , Jianfeng Chi , Eric Michael Smith , Nicholas Carlini , Florian Tramèr , Daphne Ippolito

Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research…

Cryptography and Security · Computer Science 2022-02-23 Miguel A. Ramirez , Song-Kyoo Kim , Hussam Al Hamadi , Ernesto Damiani , Young-Ji Byon , Tae-Yeon Kim , Chung-Suk Cho , Chan Yeob Yeun

We study the problem of robust learning under clean-label data-poisoning attacks, where the attacker injects (an arbitrary set of) correctly-labeled examples to the training set to fool the algorithm into making mistakes on specific test…

Machine Learning · Computer Science 2021-07-08 Avrim Blum , Steve Hanneke , Jian Qian , Han Shao

From the perspective of content safety issues, alignment has shown to limit large language models' (LLMs) harmful content generation. This intentional method of reinforcing models to not respond to certain user inputs seem to be present in…

Computation and Language · Computer Science 2023-08-28 Aibek Bekbayev , Sungbae Chun , Yerzat Dulat , James Yamazaki

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Machine Learning · Computer Science 2021-08-11 Nicholas Carlini

The unprecedented availability of training data fueled the rapid development of powerful neural networks in recent years. However, the need for such large amounts of data leads to potential threats such as poisoning attacks: adversarial…

Machine Learning · Computer Science 2024-03-21 Fabio De Gaspari , Dorjan Hitaj , Luigi V. Mancini

Data poisoning and leakage risks impede the massive deployment of federated learning in the real world. This chapter reveals the truths and pitfalls of understanding two dominating threats: {\em training data privacy intrusion} and {\em…

Machine Learning · Computer Science 2024-09-23 Wenqi Wei , Tiansheng Huang , Zachary Yahn , Anoop Singhal , Margaret Loper , Ling Liu

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

Modern machine learning pipelines leverage large amounts of public data, making it infeasible to guarantee data quality and leaving models open to poisoning and backdoor attacks. Provably bounding model behavior under such attacks remains…

Machine Learning · Computer Science 2024-10-31 Philip Sosnin , Mark N. Müller , Maximilian Baader , Calvin Tsay , Matthew Wicker

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

Machine Learning · Computer Science 2024-07-17 Quang H. Nguyen , Nguyen Ngoc-Hieu , The-Anh Ta , Thanh Nguyen-Tang , Kok-Seng Wong , Hoang Thanh-Tung , Khoa D. Doan

Ensuring the reliability of machine learning-based intrusion detection systems remains a critical challenge in Internet of Things (IoT) environments, particularly as data poisoning attacks increasingly threaten the integrity of model…

The concept of learned index structures relies on the idea that the input-output functionality of a database index can be viewed as a prediction task and, thus, be implemented using a machine learning model instead of traditional…

Cryptography and Security · Computer Science 2022-03-01 Evgenios M. Kornaropoulos , Silei Ren , Roberto Tamassia