English
Related papers

Related papers: Planting Undetectable Backdoors in Machine Learnin…

200 papers

Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…

Cryptography and Security · Computer Science 2018-08-31 Cong Liao , Haoti Zhong , Anna Squicciarini , Sencun Zhu , David Miller

Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…

Cryptography and Security · Computer Science 2025-09-24 Yuan Ma , Jiankang Wei , Yilun Lyu , Kehao Chen , Jingtong Huang

Machine learning is vulnerable to adversarial manipulation. Previous literature has demonstrated that at the training stage attackers can manipulate data and data sampling procedures to control model behaviour. A common attack goal is to…

Machine Learning · Computer Science 2022-06-17 Mikel Bober-Irizar , Ilia Shumailov , Yiren Zhao , Robert Mullins , Nicolas Papernot

Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…

Machine Learning · Computer Science 2020-06-09 Te Juin Lester Tan , Reza Shokri

As society grows more reliant on machine learning, ensuring the security of machine learning systems against sophisticated attacks becomes a pressing concern. A recent result of Goldwasser, Kim, Vaikuntanathan, and Zamir (2022) shows that…

Machine Learning · Computer Science 2024-11-06 Shafi Goldwasser , Jonathan Shafer , Neekon Vafa , Vinod Vaikuntanathan

As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by undetectable backdoors,…

Machine Learning · Computer Science 2024-09-10 Alkis Kalavasis , Amin Karbasi , Argyris Oikonomou , Katerina Sotiraki , Grigoris Velegkas , Manolis Zampetakis

Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards…

Cryptography and Security · Computer Science 2019-08-07 Eugene Bagdasaryan , Andreas Veit , Yiqing Hua , Deborah Estrin , Vitaly Shmatikov

Explainable machine learning holds great potential for analyzing and understanding learning-based systems. These methods can, however, be manipulated to present unfaithful explanations, giving rise to powerful and stealthy adversaries. In…

Cryptography and Security · Computer Science 2022-04-21 Maximilian Noppel , Lukas Peter , Christian Wressnegger

Backdoor attacks aim to inject a backdoor into a classifier such that it predicts any input with an attacker-chosen backdoor trigger as an attacker-chosen target class. Existing backdoor attacks require either retraining the classifier with…

Cryptography and Security · Computer Science 2024-12-10 Bochuan Cao , Jinyuan Jia , Chuxuan Hu , Wenbo Guo , Zhen Xiang , Jinghui Chen , Bo Li , Dawn Song

We investigate a new method for injecting backdoors into machine learning models, based on compromising the loss-value computation in the model-training code. We use it to demonstrate new classes of backdoors strictly more powerful than…

Cryptography and Security · Computer Science 2021-02-22 Eugene Bagdasaryan , Vitaly Shmatikov

The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during model deployment and can evade detection by conventional…

Foundation models have revolutionized computer vision by enabling broad generalization across diverse tasks. Yet, they remain highly susceptible to adversarial perturbations and targeted backdoor attacks. Mitigating such vulnerabilities…

Machine Learning · Computer Science 2025-10-17 Amel Abdelraheem , Alessandro Favero , Gerome Bovet , Pascal Frossard

Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in the form of backdoors during training. The goal of a backdoor is to corrupt the performance of the trained model on specific sub-tasks (e.g., by…

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…

Machine Learning · Statistics 2019-12-10 Alexander Turner , Dimitris Tsipras , Aleksander Madry

We present Sparse Backdoor, a supply-chain attack that plants a \emph{provably undetectable} backdoor in pre-trained image classifiers, including convolutional networks and Vision Transformers. The attack injects a structured sparse…

Cryptography and Security · Computer Science 2026-05-07 Sarthak Choudhary , Atharv Singh Patlan , Nils Palumbo , Ashish Hooda , Kassem Fawaz , Somesh Jha

We introduce a formal notion of defendability against backdoors using a game between an attacker and a defender. In this game, the attacker modifies a function to behave differently on a particular input known as the "trigger", while…

Machine Learning · Computer Science 2025-02-12 Paul Christiano , Jacob Hilton , Victor Lecomte , Mark Xu

In recent years, the security issues of artificial intelligence have become increasingly prominent due to the rapid development of deep learning research and applications. Backdoor attack is an attack targeting the vulnerability of deep…

Cryptography and Security · Computer Science 2023-12-14 Peixin Zhang , Jun Sun , Mingtian Tan , Xinyu Wang

In a backdoor attack on a machine learning model, an adversary produces a model that performs well on normal inputs but outputs targeted misclassifications on inputs containing a small trigger pattern. Model compression is a widely-used…

Cryptography and Security · Computer Science 2021-05-03 Yulong Tian , Fnu Suya , Fengyuan Xu , David Evans

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…

Cryptography and Security · Computer Science 2023-07-20 Alaa Khaddaj , Guillaume Leclerc , Aleksandar Makelov , Kristian Georgiev , Hadi Salman , Andrew Ilyas , Aleksander Madry

Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Felix Hsieh , Huy H. Nguyen , AprilPyone MaungMaung , Dmitrii Usynin , Isao Echizen
‹ Prev 1 2 3 10 Next ›