Related papers: QFlip: An Adaptive Reinforcement Learning Strategy…
Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms…
In this paper, we formulate the adaptive learning problem---the problem of how to find an individualized learning plan (called policy) that chooses the most appropriate learning materials based on learner's latent traits---faced in adaptive…
In the evolving digital landscape, it is crucial to study the dynamics of cyberattacks and defences. This study uses an Evolutionary Game Theory (EGT) framework to investigate the evolutionary dynamics of attacks and defences in cyberspace.…
Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have shown that the inference performance of CLIP can be greatly…
We develop a queueing-theoretic framework to model the temporal evolution of cyber-attack surfaces, where the number of active vulnerabilities is represented as the backlog of a queue. Vulnerabilities arrive as they are discovered or…
Federated learning is vulnerable to various attacks, such as model poisoning and backdoor attacks, even if some existing defense strategies are used. To address this challenge, we propose an attack-adaptive aggregation strategy to defend…
We study bandit learning in matching markets, where players and arms constitute the two market sides, and the players' utilities are linear in the arm contexts. In each round, new arms arrive with observable contexts. Then, the algorithm…
In this work, we model Moving Target Defence (MTD) as a partially observable stochastic game between an attacker and a defender. The attacker tries to compromise the system through probing actions, while the defender minimizes the risk by…
Adversarial attacks pose significant threats to the reliability and safety of deep learning models, especially in critical domains such as medical imaging. This paper introduces a novel framework that integrates conformal prediction with…
We study automated intrusion response and formulate the interaction between an attacker and a defender as an optimal stopping game where attack and defense strategies evolve through reinforcement learning and self-play. The game-theoretic…
The vulnerability of deep neural network models to adversarial example attacks is a practical challenge in many artificial intelligence applications. A recent line of work shows that the use of randomization in adversarial training is the…
Adversarial Patrolling games form a subclass of Security games where a Defender moves between locations, guarding vulnerable targets. The main algorithmic problem is constructing a strategy for the Defender that minimizes the worst damage…
Advanced Persistent Threats (APTs) are stealthy, multi-stage attacks that require adaptive and timely defense. While deep reinforcement learning (DRL) enables autonomous cyber defense, its decisions are often opaque and difficult to trust…
We propose an adaptive incentive mechanism that learns the optimal incentives in environments where players continuously update their strategies. Our mechanism updates incentives based on each player's externality, defined as the difference…
In reward-poisoning attacks against reinforcement learning (RL), an attacker can perturb the environment reward $r_t$ into $r_t+\delta_t$ at each step, with the goal of forcing the RL agent to learn a nefarious policy. We categorize such…
Adversarial training in reinforcement learning (RL) is challenging because perturbations cascade through trajectories and compound over time, making fixed-strength attacks either overly destructive or too conservative. We propose…
We present an efficient algorithm for model-free episodic reinforcement learning on large (potentially continuous) state-action spaces. Our algorithm is based on a novel $Q$-learning policy with adaptive data-driven discretization. The…
Meta-reinforcement learning algorithms provide a data-driven way to acquire policies that quickly adapt to many tasks with varying rewards or dynamics functions. However, learned meta-policies are often effective only on the exact task…
Despite its remarkable success in zero-shot image-text matching, CLIP remains highly vulnerable to adversarial perturbations on images. As adversarial fine-tuning is prohibitively costly, recent works explore various test-time defense…
Punishment is a common tactic to sustain cooperation and has been extensively studied for a long time. While most of previous game-theoretic work adopt the imitation learning where players imitate the strategies who are better off, the…