Related papers: Evolving Reinforcement Learning Environment to Min…
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…
We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults, sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt…
Asymmetrical multiplayer (AMP) game is a popular game genre which involves multiple types of agents competing or collaborating with each other in the game. It is difficult to train powerful agents that can defeat top human players in AMP…
Reinforcement learning is commonly concerned with problems of maximizing accumulated rewards in Markov decision processes. Oftentimes, a certain goal state or a subset of the state space attain maximal reward. In such a case, the…
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…
Deep learning has emerged as a leading approach for Automatic Modulation Classification (AMC), demonstrating superior performance over traditional methods. However, vulnerability to adversarial attacks and susceptibility to data…
The Transformer, a highly expressive architecture for sequence modeling, has recently been adapted to solve sequential decision-making, most notably through the Decision Transformer (DT), which learns policies by conditioning on desired…
Reinforcement Learning (RL), one of the core paradigms in machine learning, learns to make decisions based on real-world experiences. This approach has significantly advanced AI applications across various domains, notably in smart grid…
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) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. However, effective agentic RL remains challenging: sparse outcome-only rewards…
Moving target defense (MTD) is a proactive defense approach that aims to thwart attacks by continuously changing the attack surface of a system (e.g., changing host or network configurations), thereby increasing the adversary's uncertainty…
Recent applications of Stackelberg Security Games (SSG), from wildlife crime to urban crime, have employed machine learning tools to learn and predict adversary behavior using available data about defender-adversary interactions. Given…
Many cooperative multiagent reinforcement learning environments provide agents with a sparse team-based reward, as well as a dense agent-specific reward that incentivizes learning basic skills. Training policies solely on the team-based…
Evolutionary algorithms have been used to evolve a population of actors to generate diverse experiences for training reinforcement learning agents, which helps to tackle the temporal credit assignment problem and improves the exploration…
Batch reinforcement learning (RL) defines the task of learning from a fixed batch of data lacking exhaustive exploration. Worst-case optimality algorithms, which calibrate a value-function model class from logged experience and perform some…
As machine learning models become more capable, they have exhibited increased potential in solving complex tasks. One of the most promising directions uses deep reinforcement learning to train autonomous agents in computer network defense…
Deep Reinforcement Learning (DRL) has emerged as a promising approach for solving Combinatorial Optimization (CO) problems, such as the 3D Bin Packing Problem (3D-BPP), Traveling Salesman Problem (TSP), or Vehicle Routing Problem (VRP), but…
Reinforcement Learning (RL) is an area of machine learning figuring out how agents take actions in an unknown environment to maximize its rewards. Unlike classical Markov Decision Process (MDP) in which agent has full knowledge of its…
Recent works have shown that the input domain of any machine learning classifier is bound to contain adversarial examples. Thus we can no longer hope to immune classifiers against adversarial examples and instead can only aim to achieve the…
Reinforcement Learning (RL) algorithms have been successfully applied to real world situations like illegal smuggling, poaching, deforestation, climate change, airport security, etc. These scenarios can be framed as Stackelberg security…