Related papers: Testing the Robustness of Learned Index Structures

Recent advances in federated learning have demonstrated its promising capability to learn on decentralized datasets. However, a considerable amount of work has raised concerns due to the potential risks of adversaries participating in the…

Machine learning models are brittle, and small changes in the training data can result in different predictions. We study the problem of proving that a prediction is robust to data poisoning, where an attacker can inject a number of…

In federated learning, multiple client devices jointly learn a machine learning model: each client device maintains a local model for its local training dataset, while a master device maintains a global model via aggregating the local…

Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers. While most work has defended against a single type of…

Federated Learning has emerged as a dominant computational paradigm for distributed machine learning. Its unique data privacy properties allow us to collaboratively train models while offering participating clients certain…

Collective learning methods exploit relations among data points to enhance classification performance. However, such relations, represented as edges in the underlying graphical model, expose an extra attack surface to the adversaries. We…

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

Research in adversarial machine learning (AML) has shown that statistical models are vulnerable to maliciously altered data. However, despite advances in Bayesian machine learning models, most AML research remains concentrated on classical…

Federated Learning (FL) is a paradigm in Machine Learning (ML) that addresses data privacy, security, access rights and access to heterogeneous information issues by training a global model using distributed nodes. Despite its advantages,…

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…

This demo paper examines the susceptibility of Federated Learning (FL) systems to targeted data poisoning attacks, presenting a novel system for visualizing and mitigating such threats. We simulate targeted data poisoning attacks via label…

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify…

Federated Learning (FL) is a distributed machine learning diagram that enables multiple clients to collaboratively train a global model without sharing their private local data. However, FL systems are vulnerable to attacks that are…

It is well-known that deep learning models are vulnerable to small input perturbations. Such perturbed instances are called adversarial examples. Adversarial examples are commonly crafted to fool a model either at training time (poisoning)…

As pairwise ranking becomes broadly employed for elections, sports competitions, recommendations, and so on, attackers have strong motivation and incentives to manipulate the ranking list. They could inject malicious comparisons into the…

Evaluating robustness of machine-learning models to adversarial examples is a challenging problem. Many defenses have been shown to provide a false sense of robustness by causing gradient-based attacks to fail, and they have been broken…

Algorithms are increasingly common components of high-impact decision-making, and a growing body of literature on adversarial examples in laboratory settings indicates that standard machine learning models are not robust. This suggests that…

Federated learning---multi-party, distributed learning in a decentralized environment---is vulnerable to model poisoning attacks, even more so than centralized learning approaches. This is because malicious clients can collude and send in…

Various attack methods against recommender systems have been proposed in the past years, and the security issues of recommender systems have drawn considerable attention. Traditional attacks attempt to make target items recommended to as…

Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations…