Related papers: Adversarial Agents: Black-Box Evasion Attacks with…
Extensive research demonstrates that Deep Reinforcement Learning (DRL) models are susceptible to adversarially constructed inputs (i.e., adversarial examples), which can mislead the agent to take suboptimal or unsafe actions. Recent methods…
In several reinforcement learning (RL) scenarios, mainly in security settings, there may be adversaries trying to interfere with the reward generating process. In this paper, we introduce Threatened Markov Decision Processes (TMDPs), which…
Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model. Recently, white-box model inversion attacks leveraging Generative Adversarial…
The widespread adoption of smartphones dramatically increases the risk of attacks and the spread of mobile malware, especially on the Android platform. Machine learning-based solutions have been already used as a tool to supersede…
The vulnerability of the high-performance machine learning models implies a security risk in applications with real-world consequences. Research on adversarial attacks is beneficial in guiding the development of machine learning models on…
Despite the impressive performances reported by deep neural networks in different application domains, they remain largely vulnerable to adversarial examples, i.e., input samples that are carefully perturbed to cause misclassification at…
Deep reinforcement learning has shown promising results in learning control policies for complex sequential decision-making tasks. However, these neural network-based policies are known to be vulnerable to adversarial examples. This…
Autoregressive models recently achieved comparable results versus state-of-the-art Generative Adversarial Networks (GANs) with the help of Vector Quantized Variational AutoEncoders (VQ-VAE). However, autoregressive models have several…
Modern algorithms in the domain of Deep Reinforcement Learning (DRL) demonstrated remarkable successes; most widely known are those in game-based scenarios, from ATARI video games to Go and the StarCraft~\textsc{II} real-time strategy game.…
Reinforcement learning (RL) offers significant promise for machinery fault detection (MFD). However, most existing RL-based MFD approaches do not fully exploit RL's sequential decision-making strengths, often treating MFD as a simple…
Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…
Advances in deep learning have enabled a wide range of promising applications. However, these systems are vulnerable to Adversarial Machine Learning (AML) attacks; adversarially crafted perturbations to their inputs could cause them to…
We study a search and tracking (S&T) problem where a team of dynamic search agents must collaborate to track an adversarial, evasive agent. The heterogeneous search team may only have access to a limited number of past adversary…
This study investigates a counterintuitive phenomenon in adversarial machine learning: the potential for noise-based defenses to inadvertently aid evasion attacks in certain scenarios. While randomness is often employed as a defensive…
Reinforcement learning (RL) provides a naturalistic framing for learning through trial and error, which is appealing both because of its simplicity and effectiveness and because of its resemblance to how humans and animals acquire skills…
Latent-factor models (LFM) based on collaborative filtering (CF), such as matrix factorization (MF) and deep CF methods, are widely used in modern recommender systems (RS) due to their excellent performance and recommendation accuracy.…
Unsupervised reinforcement learning (RL) studies how to leverage environment statistics to learn useful behaviors without the cost of reward engineering. However, a central challenge in unsupervised RL is to extract behaviors that…
This paper presents the first model extraction attack against Deep Reinforcement Learning (DRL), which enables an external adversary to precisely recover a black-box DRL model only from its interaction with the environment. Model extraction…
Adversarial examples represent a serious issue for the application of machine learning models in many sensitive domains. For generating adversarial examples, decision based black-box attacks are one of the most practical techniques as they…
Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture the desired behavior of a system, especially when dealing…