Related papers: Reinforcement Learning-based Black-Box Evasion Att…

Graph Neural Networks (GNNs) have been widely used for graph analysis. Federated Graph Learning (FGL) is an emerging learning framework to collaboratively train graph data from various clients. Although FGL allows client data to remain…

Electrical faults may trigger blackouts or wildfires without timely monitoring and control strategy. Traditional solutions for locating faults in distribution systems are not real-time when network observability is low, while novel…

The successful emergence of deep learning (DL) in wireless system applications has raised concerns about new security-related challenges. One such security challenge is adversarial attacks. Although there has been much work demonstrating…

Adversarial attacks pose significant challenges for detecting adversarial attacks at an early stage. We propose attack-agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft adversarial…

Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples can be generalised from White-box and Grey-box attacks to a…

The vulnerability of deep neural networks (DNNs) to adversarial examples has drawn great attention from the community. In this paper, we study the transferability of such examples, which lays the foundation of many black-box attacks on…

Deep learning has been rapidly employed in many applications revolutionizing many industries, but it is known to be vulnerable to adversarial attacks. Such attacks pose a serious threat to deep learning-based systems compromising their…

Graph Neural Networks (GNNs) have been widely applied to different tasks such as bioinformatics, drug design, and social networks. However, recent studies have shown that GNNs are vulnerable to adversarial attacks which aim to mislead the…

Text-attributed graphs (TAGs), which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models (LLMs) with Graph Neural Networks (GNNs) to jointly model semantics and…

The temporal dynamics of a complex system such as a social network or a communication network can be studied by understanding the patterns of link appearance and disappearance over time. A critical task along this understanding is to…

A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well…

We propose the first black-box targeted attack against online deep reinforcement learning through reward poisoning during training time. Our attack is applicable to general environments with unknown dynamics learned by unknown algorithms…

Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications -- making it paramount to ensure the robustness of RL algorithms against adversarial attacks. In this work…

Graph Neural Networks (GNNs) have achieved promising results in various tasks such as node classification and graph classification. Recent studies find that GNNs are vulnerable to adversarial attacks. However, effective backdoor attacks on…

Dynamic multi-relational graphs are an expressive relational representation for data enclosing entities and relations of different types, and where relationships are allowed to vary in time. Addressing predictive tasks over such data…

Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human…

Trajectory prediction systems are critical for autonomous vehicle safety, yet remain vulnerable to adversarial attacks that can cause catastrophic traffic behavior misinterpretations. Existing attack methods require white-box access with…

Machine Learning (ML) models are susceptible to evasion attacks. Evasion accuracy is typically assessed using aggregate evasion rate, and it is an open question whether aggregate evasion rate enables feature-level diagnosis on the effect of…

The successes of deep Reinforcement Learning (RL) are limited to settings where we have a large stream of online experiences, but applying RL in the data-efficient setting with limited access to online interactions is still challenging. A…

With the increase of data in day-to-day life, businesses and different stakeholders need to analyze the data for better predictions. Traditionally, relational data has been a source of various insights, but with the increase in…