English
Related papers

Related papers: Planting Undetectable Backdoors in Machine Learnin…

200 papers

Backdoor data poisoning is an emerging form of adversarial attack usually against deep neural network image classifiers. The attacker poisons the training set with a relatively small set of images from one (or several) source class(es),…

Machine Learning · Computer Science 2020-10-16 Zhen Xiang , David J. Miller , George Kesidis

Deep neural networks are vulnerable to a range of adversaries. A particularly pernicious class of vulnerabilities are backdoors, where model predictions diverge in the presence of subtle triggers in inputs. An attacker can implant a…

Machine Learning · Computer Science 2022-12-20 Goutham Ramakrishnan , Aws Albarghouthi

Detecting semantic backdoors in classification models--where some classes can be activated by certain natural, but out-of-distribution inputs--is an important problem that has received relatively little attention. Semantic backdoors are…

Machine Learning · Computer Science 2026-01-08 Arpad Berta , Gabor Danner , Istvan Hegedus , Mark Jelasity

Federated learning (FL) has been widely adopted as a decentralized training paradigm that enables multiple clients to collaboratively learn a shared model without exposing their local data. As concerns over data privacy and regulatory…

Cryptography and Security · Computer Science 2025-08-22 Bingguang Lu , Hongsheng Hu , Yuantian Miao , Shaleeza Sohail , Chaoxiang He , Shuo Wang , Xiao Chen

In this brief, we show that sequentially learning new information presented to a continual (incremental) learning model introduces new security risks: an intelligent adversary can introduce small amount of misinformation to the model during…

Machine Learning · Computer Science 2022-02-10 Muhammad Umer , Robi Polikar

Class incremental learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, it has been shown that such approaches are…

Machine Learning · Computer Science 2023-05-01 Muhammad Umer , Robi Polikar

Early backdoor attacks against machine learning set off an arms race in attack and defence development. Defences have since appeared demonstrating some ability to detect backdoors in models or even remove them. These defences work by…

Machine Learning · Computer Science 2024-06-03 Eleanor Clifford , Ilia Shumailov , Yiren Zhao , Ross Anderson , Robert Mullins

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

Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific $\textit{trigger}$, it behaves as the attacker desires. Detecting such triggers…

Cryptography and Security · Computer Science 2026-03-12 Eirik Høyheim , Magnus Wiik Eckhoff , Gudmund Grov , Robert Flood , David Aspinall

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…

Cryptography and Security · Computer Science 2023-10-19 Ganghua Wang , Xun Xian , Jayanth Srinivasa , Ashish Kundu , Xuan Bi , Mingyi Hong , Jie Ding

Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by…

Cryptography and Security · Computer Science 2022-02-17 Yiming Li , Yong Jiang , Zhifeng Li , Shu-Tao Xia

Federated Learning (FL) enables numerous participants to train deep learning models collaboratively without exposing their personal, potentially sensitive data, making it a promising solution for data privacy in collaborative training. The…

Cryptography and Security · Computer Science 2022-06-02 Manaar Alam , Esha Sarkar , Michail Maniatakos

Deep learning-based techniques have achieved state-of-the-art performance on a wide variety of recognition and classification tasks. However, these networks are typically computationally expensive to train, requiring weeks of computation on…

Cryptography and Security · Computer Science 2019-03-13 Tianyu Gu , Brendan Dolan-Gavitt , Siddharth Garg

It is common practice to outsource the training of machine learning models to cloud providers. Clients who do so gain from the cloud's economies of scale, but implicitly assume trust: the server should not deviate from the client's training…

Cryptography and Security · Computer Science 2025-04-02 Hengrui Jia , Sierra Wyllie , Akram Bin Sediq , Ahmed Ibrahim , Nicolas Papernot

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

In a federated learning (FL) system, decentralized data owners (clients) could upload their locally trained models to a central server, to jointly train a global model. Malicious clients may plant backdoors into the global model through…

Cryptography and Security · Computer Science 2024-06-03 Songze Li , Yanbo Dai

Recent cryptographic results establish that neural networks can be backdoored such that no efficient algorithm can distinguish them from a clean model. These guarantees, however, have been confined to stylised architectures of limited…

Cryptography and Security · Computer Science 2026-05-14 Marte Eggen , Eirik Reiestad , Kristian Gjøsteen , Inga Strümke

Under a commonly-studied backdoor poisoning attack against classification models, an attacker adds a small trigger to a subset of the training data, such that the presence of this trigger at test time causes the classifier to always predict…

Machine Learning · Computer Science 2021-10-06 Mingjie Sun , Siddhant Agarwal , J. Zico Kolter

Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broaden the use of ML models, cloud-based services offered by…

Machine Learning · Computer Science 2017-03-14 Hossein Hosseini , Yize Chen , Sreeram Kannan , Baosen Zhang , Radha Poovendran

Machine unlearning has emerged as a key component in ensuring ``Right to be Forgotten'', enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set…

Cryptography and Security · Computer Science 2025-06-17 Marco Arazzi , Antonino Nocera , Vinod P