English
Related papers

Related papers: Mole Recruitment: Poisoning of Image Classifiers v…

200 papers

Data poisoning attacks on machine learning models aim to manipulate the data used for model training such that the trained model behaves in the attacker's favour. In classical models such as deep neural networks, large chains of dot…

The attacks on the neural-network-based classifiers using adversarial images have gained a lot of attention recently. An adversary can purposely generate an image that is indistinguishable from a innocent image for a human being but is…

Cryptography and Security · Computer Science 2019-07-02 Nir Morgulis , Alexander Kreines , Shachar Mendelowitz , Yuval Weisglass

In spam and malware detection, attackers exploit randomization to obfuscate malicious data and increase their chances of evading detection at test time; e.g., malware code is typically obfuscated using random strings or byte sequences to…

Machine Learning · Computer Science 2016-09-07 Samuel Rota Bulò , Battista Biggio , Ignazio Pillai , Marcello Pelillo , Fabio Roli

In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets…

Machine Learning · Computer Science 2018-11-16 Matthew Klawonn , Eric Heim , James Hendler

Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled.…

Computer Vision and Pattern Recognition · Computer Science 2022-06-07 Pengfei Xia , Ziqiang Li , Wei Zhang , Bin Li

Machine learning models have achieved great success in supervised learning tasks for end-to-end training, which requires a large amount of labeled data that is not always feasible. Recently, many practitioners have shifted to…

Machine Learning · Computer Science 2024-02-21 Yiwei Lu , Matthew Y. R. Yang , Gautam Kamath , Yaoliang Yu

Making learners robust to adversarial perturbation at test time (i.e., evasion attacks) or training time (i.e., poisoning attacks) has emerged as a challenging task. It is known that for some natural settings, sublinear perturbations in the…

Machine Learning · Computer Science 2018-11-07 Saeed Mahloujifar , Mohammad Mahmoody

Adversarial Machine Learning has emerged as a substantial subfield of Computer Science due to a lack of robustness in the models we train along with crowdsourcing practices that enable attackers to tamper with data. In the last two years,…

Machine Learning · Computer Science 2021-07-29 Jacob Dineen , A S M Ahsan-Ul Haque , Matthew Bielskas

A backdoor data poisoning attack is an adversarial attack wherein the attacker injects several watermarked, mislabeled training examples into a training set. The watermark does not impact the test-time performance of the model on typical…

Machine Learning · Computer Science 2021-11-05 Naren Sarayu Manoj , Avrim Blum

Inference attacks against Machine Learning (ML) models allow adversaries to learn sensitive information about training data, model parameters, etc. While researchers have studied, in depth, several kinds of attacks, they have done so in…

Cryptography and Security · Computer Science 2021-10-07 Yugeng Liu , Rui Wen , Xinlei He , Ahmed Salem , Zhikun Zhang , Michael Backes , Emiliano De Cristofaro , Mario Fritz , Yang Zhang

Image generation has shown remarkable results in generating high-fidelity realistic images, in particular with the advancement of diffusion-based models. However, the prevalence of AI-generated images may have side effects for the machine…

Computer Vision and Pattern Recognition · Computer Science 2024-11-22 Maorong Wang , Nicolas Michel , Jiafeng Mao , Toshihiko Yamasaki

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

In the domain of large language models (LLMs), in-context learning (ICL) has been recognized for its innovative ability to adapt to new tasks, relying on examples rather than retraining or fine-tuning. This paper delves into the critical…

Cryptography and Security · Computer Science 2025-06-03 Pengfei He , Han Xu , Yue Xing , Hui Liu , Makoto Yamada , Jiliang Tang

Many of today's machine learning (ML) systems are built by reusing an array of, often pre-trained, primitive models, each fulfilling distinct functionality (e.g., feature extraction). The increasing use of primitive models significantly…

Cryptography and Security · Computer Science 2018-12-04 Yujie Ji , Xinyang Zhang , Shouling Ji , Xiapu Luo , Ting Wang

Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…

Machine Learning · Computer Science 2019-11-26 Arjun Nitin Bhagoji , Supriyo Chakraborty , Prateek Mittal , Seraphin Calo

With the rapid growth of the number of devices on the Internet, malware poses a threat not only to the affected devices but also their ability to use said devices to launch attacks on the Internet ecosystem. Rapid malware classification is…

Cryptography and Security · Computer Science 2021-07-30 Hikmat Farhat , Veronica Rammouz

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Cryptography and Security · Computer Science 2023-06-30 Nils Lukas , Florian Kerschbaum

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

Gradient attacks and data poisoning tamper with the training of machine learning algorithms to maliciously alter them and have been proven to be equivalent in convex settings. The extent of harm these attacks can produce in non-convex…

Machine Learning · Computer Science 2024-12-12 Wassim Bouaziz , El-Mahdi El-Mhamdi , Nicolas Usunier

Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model…

Machine Learning · Computer Science 2020-06-29 David Solans , Battista Biggio , Carlos Castillo