Related papers: Model Extraction Attacks Against Reinforcement Lea…

Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed queries can be severely limited. In this paper, we demonstrate…

Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples. While numerous successful adversarial attacks have been proposed, defenses against these attacks remain relatively understudied. Existing defense…

Neural networks are valuable intellectual property due to the significant computational cost, expert labor, and proprietary data involved in their development. Consequently, protecting their parameters is critical not only for maintaining a…

Deep neural network (DNN) classifiers are powerful tools that drive a broad spectrum of important applications, from image recognition to autonomous vehicles. Unfortunately, DNNs are known to be vulnerable to adversarial attacks that affect…

While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being…

Reinforcement Learning (RL) methods that incorporate deep neural networks (DNN), though powerful, often lack transparency. Their black-box characteristic hinders interpretability and reduces trustworthiness, particularly in critical…

Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantage to its owner, and (b) an adversary may use a stolen model…

The internal functional behavior of trained Deep Neural Networks is notoriously difficult to interpret. Activation-maximization approaches are one set of techniques used to interpret and analyze trained deep-learning models. These consist…

Despite the successful application of machine learning (ML) in a wide range of domains, adaptability---the very property that makes machine learning desirable---can be exploited by adversaries to contaminate training and evade…

Deep Neural Networks (DNNs) have become ubiquitous due to their performance on prediction and classification problems. However, they face a variety of threats as their usage spreads. Model extraction attacks, which steal DNNs, endanger…

Graph Neural Networks (GNNs) are recognized as potent tools for processing real-world data organized in graph structures. Especially inductive GNNs, which allow for the processing of graph-structured data without relying on predefined graph…

Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time. In this work, we show that these training-time vulnerabilities extend to deep…

Continuous control Deep Reinforcement Learning (RL) approaches are known to suffer from estimation biases, leading to suboptimal policies. This paper introduces innovative methods in RL, focusing on addressing and exploiting estimation…

Model-Free Reinforcement Learning (RL) algorithms either learn how to map states to expected rewards or search for policies that can maximize a certain performance function. Model-Based algorithms instead, aim to learn an approximation of…

Deep neural network (DNN) classifiers are vulnerable to backdoor attacks. An adversary poisons some of the training data in such attacks by installing a trigger. The goal is to make the trained DNN output the attacker's desired class…

With the increasing amount of available data and advances in computing capabilities, deep neural networks (DNNs) have been successfully employed to solve challenging tasks in various areas, including healthcare, climate, and finance.…

We propose a novel deep neural network (DNN) based approximation architecture to learn estimates of measurements. We detail an algorithm that enables training of the DNN. The DNN estimator only uses measurements, if and when they are…

The recent breakthroughs of deep reinforcement learning (DRL) technique in Alpha Go and playing Atari have set a good example in handling large state and actions spaces of complicated control problems. The DRL technique is comprised of (i)…

To ensure the usefulness of Reinforcement Learning (RL) in real systems, it is crucial to ensure they are robust to noise and adversarial attacks. In adversarial RL, an external attacker has the power to manipulate the victim agent's…

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…