Related papers: Interactive Trimming against Evasive Online Data M…

Targeted interventions in games present a challenging problem due to the asymmetric information available to the regulator and the agents. This note addresses the problem of steering the actions of self-interested agents in quadratic…

Adversarial attacks pose significant threats to the reliability and safety of deep learning models, especially in critical domains such as medical imaging. This paper introduces a novel framework that integrates conformal prediction with…

Link prediction in dynamic graphs (LPDG) has been widely applied to real-world applications such as website recommendation, traffic flow prediction, organizational studies, etc. These models are usually kept local and secure, with only the…

There is an upward trend of deploying distributed energy resource management systems (DERMS) to control modern power grids. However, DERMS controller communication lines are vulnerable to cyberattacks that could potentially impact…

Data ecosystems are becoming larger and more complex due to online tracking, wearable computing, and the Internet of Things. But privacy concerns are threatening to erode the potential benefits of these systems. Recently, users have…

The security in networked systems depends greatly on recognizing and identifying adversarial behaviors. Traditional detection methods focus on specific categories of attacks and have become inadequate for increasingly stealthy and deceptive…

As large language models (LLMs) grow more capable, concerns about their safe deployment have also grown. Although alignment mechanisms have been introduced to deter misuse, they remain vulnerable to carefully designed adversarial prompts.…

Data poisoning is an adversarial scenario where an attacker feeds a specially crafted sequence of samples to an online model in order to subvert learning. We introduce Lethean Attack, a novel data poisoning technique that induces…

Advanced persistent threats (APT) combine a variety of different attack forms ranging from social engineering to technical exploits. The diversity and usual stealthiness of APT turns them into a central problem of contemporary practical…

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

The expansion of large-scale online education platforms has made vast amounts of student interaction data available for knowledge tracing (KT). KT models estimate students' concept mastery from interaction data, but their performance is…

Federated Learning systems are increasingly subjected to a multitude of model poisoning attacks from clients. Among these, edge-case attacks that target a small fraction of the input space are nearly impossible to detect using existing…

With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the…

Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms…

There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning…

Machine learning systems trained on user-provided data are susceptible to data poisoning attacks, whereby malicious users inject false training data with the aim of corrupting the learned model. While recent work has proposed a number of…

This paper presents a method that addresses the conservatism, computational effort, and limited numerical accuracy of existing frameworks and methods that ensure safety in online model-based motion generation, commonly referred to as fast…

Data lakes enable the training of powerful machine learning models on sensitive, high-value medical datasets, but also introduce serious privacy risks due to potential leakage of protected health information. Recent studies show adversaries…

In this paper we use game theory to model poisoning attack scenarios. We prove the non-existence of pure strategy Nash Equilibrium in the attacker and defender game. We then propose a mixed extension of our game model and an algorithm to…

Data poisoning causes misclassification of test time target examples by injecting maliciously crafted samples in the training data. Existing defenses are often effective only against a specific type of targeted attack, significantly degrade…