English
Related papers

Related papers: Interactive Trimming against Evasive Online Data M…

200 papers

Despite its success and popularity, machine learning is now recognized as vulnerable to evasion attacks, i.e., carefully crafted perturbations of test inputs designed to force prediction errors. In this paper we focus on evasion attacks…

Machine Learning · Computer Science 2019-07-04 Stefano Calzavara , Claudio Lucchese , Gabriele Tolomei , Seyum Assefa Abebe , Salvatore Orlando

Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy. When trained on offline datasets, poisoning adversaries have…

Machine Learning · Computer Science 2021-10-27 Tianyu Pang , Xiao Yang , Yinpeng Dong , Hang Su , Jun Zhu

Distillation attacks create a deployment trade-off for model providers: the same outputs that make a model more useful can also make it easier to imitate. We study this trade-off through a minimax game between a utility-constrained teacher…

Machine Learning · Computer Science 2026-05-29 Youssef Allouah , Mahdi Haghifam , Sanmi Koyejo , Reza Shokri

In modern transportation networks, adversaries can manipulate routing algorithms using false data injection attacks, such as simulating heavy traffic with multiple devices running crowdsourced navigation applications, to mislead vehicles…

Artificial Intelligence · Computer Science 2026-03-13 Taha Eghtesad , Yevgeniy Vorobeychik , Aron Laszka

Deep Neural Networks (DNN) are susceptible to backdoor attacks where malicious attackers manipulate the model's predictions via data poisoning. It is hence imperative to develop a strategy for training a clean model using a potentially…

Cryptography and Security · Computer Science 2023-12-21 Yiming Chen , Haiwei Wu , Jiantao Zhou

With the rapid expansion of data lakes storing health data and hosting AI algorithms, a prominent concern arises: how safe is it to export machine learning models from these data lakes? In particular, deep network models, widely used for…

Cryptography and Security · Computer Science 2025-12-09 Huiyu Li , Nicholas Ayache , Hervé Delingette

Decentralized Federated Learning (DFL), a paradigm for managing big data in a privacy-preserved manner, is still vulnerable to poisoning attacks where malicious clients tamper with data or models. Current defense methods often assume…

Cryptography and Security · Computer Science 2024-11-13 Chao Feng , Alberto Huertas Celdrán , Zien Zeng , Zi Ye , Jan von der Assen , Gerome Bovet , Burkhard Stiller

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

Cryptography and Security · Computer Science 2020-09-02 Shadi Rahimian , Tribhuvanesh Orekondy , Mario Fritz

Pretrained language models sometimes possess knowledge that we do not wish them to, including memorized personal information and knowledge that could be used to harm people. They can also output toxic or harmful text. To mitigate these…

Computation and Language · Computer Science 2023-10-02 Vaidehi Patil , Peter Hase , Mohit Bansal

Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into…

Cryptography and Security · Computer Science 2023-10-31 Manli Shu , Jiongxiao Wang , Chen Zhu , Jonas Geiping , Chaowei Xiao , Tom Goldstein

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

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Cryptography and Security · Computer Science 2024-10-16 Shaokui Wei , Hongyuan Zha , Baoyuan Wu

Adversarial Missingness (AM) attacks aim to manipulate model fitting by carefully engineering a missing data problem to achieve a specific malicious objective. AM attacks are significantly different from prior data poisoning attacks in that…

Machine Learning · Computer Science 2025-11-18 Deniz Koyuncu , Alex Gittens , Bülent Yener , Moti Yung

Machine learning algorithms are used to construct a mathematical model for a system based on training data. Such a model is capable of making highly accurate predictions without being explicitly programmed to do so. These techniques have a…

Cryptography and Security · Computer Science 2022-02-22 Cato Pauling , Michael Gimson , Muhammed Qaid , Ahmad Kida , Basel Halak

Nowadays, numerous applications incorporate machine learning (ML) algorithms due to their prominent achievements. However, many studies in the field of computer vision have shown that ML can be fooled by intentionally crafted instances,…

Cryptography and Security · Computer Science 2023-03-14 Islam Debicha , Benjamin Cochez , Tayeb Kenaza , Thibault Debatty , Jean-Michel Dricot , Wim Mees

This paper investigates the susceptibility to model integrity attacks that overload virtual machines assigned by the k-means algorithm used for resource provisioning in fog networks. The considered k-means algorithm runs two phases…

Cryptography and Security · Computer Science 2026-03-27 Younes Salmi , Hanna Bogucka

Backdoor attacks change a small portion of training data by introducing hand-crafted triggers and rewiring the corresponding labels towards a desired target class. Training on such data injects a backdoor which causes malicious inference in…

Machine Learning · Computer Science 2024-09-05 Ivan Sabolić , Ivan Grubišić , Siniša Šegvić

The principles of statistical mechanics and information theory play an important role in learning and have inspired both theory and the design of numerous machine learning algorithms. The new aspect in this paper is a focus on integrating…

Data Analysis, Statistics and Probability · Physics 2015-05-13 Susanne Still

Local Differential Privacy (LDP) has been widely adopted to protect user privacy in decentralized data collection. However, recent studies have revealed that LDP protocols are vulnerable to data poisoning attacks, where malicious users…

Cryptography and Security · Computer Science 2025-03-07 Ting-Wei Liao , Chih-Hsun Lin , Yu-Lin Tsai , Takao Murakami , Chia-Mu Yu , Jun Sakuma , Chun-Ying Huang , Hiroaki Kikuchi

While numerous defense methods have been proposed to prohibit potential poisoning attacks from untrusted data sources, most research works only defend against specific attacks, which leaves many avenues for an adversary to exploit. In this…

Machine Learning · Computer Science 2023-11-23 Minh-Hao Van , Alycia N. Carey , Xintao Wu