Related papers: Reasoning about Moving Target Defense in Attack Mo…

Recent adversarial attack developments have made reinforcement learning more vulnerable, and different approaches exist to deploy attacks against it, where the key is how to choose the right timing of the attack. Some work tries to design…

Diffusion models (DMs) have achieved state-of-the-art performance on various generative tasks such as image synthesis, text-to-image, and text-guided image-to-image generation. However, the more powerful the DMs, the more harmful they…

This work studies a dynamic, adversarial resource allocation problem in environments modeled as graphs. A blue team of defender robots are deployed in the environment to protect the nodes from a red team of attacker robots. We formulate the…

We consider a variant of the target defense problem where a single defender is tasked to capture a sequence of incoming intruders. Both the defender and the intruders have non-holonomic dynamics. The intruders' objective is to breach the…

Stackelberg security game models and associated computational tools have seen deployment in a number of high-consequence security settings, such as LAX canine patrols and Federal Air Marshal Service. These models focus on isolated systems…

Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the state of an agent's environment does not change during action…

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

Despite the considerable performance improvements of face recognition algorithms in recent years, the same scientific advances responsible for this progress can also be used to create efficient ways to attack them, posing a threat to their…

It is a major task to develop effective strategies for defending the power system against deliberate attacks. It is critical to comprehensively consider the human-related and environmental risks and uncertainties, which is missing in…

Network defenders face a steady stream of attacks, observed as raw Intrusion Detection System (IDS) alerts. The sheer volume of alerts demands prioritization, typically based on high-level risk classifications. This work expands the scope…

We implemented and evaluated an automated cyber defense agent. The agent takes security alerts as input and uses reinforcement learning to learn a policy for executing predefined defensive measures. The defender policies were trained in an…

In Stackelberg security games when information about the attacker's payoffs is uncertain, algorithms have been proposed to learn the optimal defender commitment by interacting with the attacker and observing their best responses. In this…

The problem of offline reinforcement learning focuses on learning a good policy from a log of environment interactions. Past efforts for developing algorithms in this area have revolved around introducing constraints to online reinforcement…

Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks. This increases the importance of robust training of 3D models in the face of…

The unmanned aerial vehicle (UAV)-enabled communication technology is regarded as an efficient and effective solution for some special application scenarios where existing terrestrial infrastructures are overloaded to provide reliable…

In recent years, machine learning models have been shown to be vulnerable to backdoor attacks. Under such attacks, an adversary embeds a stealthy backdoor into the trained model such that the compromised models will behave normally on clean…

Traditionally, Reinforcement Learning (RL) aims at deciding how to act optimally for an artificial agent. We argue that deciding when to act is equally important. As humans, we drift from default, instinctive or memorized behaviors to…

Modern treatment targeting methods often rely on estimating the conditional average treatment effect (CATE) using machine learning tools. While effective in identifying who benefits from treatment on the individual level, these approaches…

This paper studies the multi-agent coverage control (MAC) problem where agents must dynamically learn an unknown density function while performing coverage tasks. Unlike many current theoretical frameworks that concentrate solely on the…

Decision Transformer (DT), which integrates reinforcement learning (RL) with the transformer model, introduces a novel approach to offline RL. Unlike classical algorithms that take maximizing cumulative discounted rewards as objective, DT…