相关论文: When to Reset Your Keys: Optimal Timing of Securit…

Security questions are one of the mechanisms used to recover passwords. Strong answers to security questions (i.e. high entropy) are hard for attackers to guess or obtain using social engineering techniques (e.g. monitoring of social…

The desire to use reinforcement learning in safety-critical settings has inspired a recent interest in formal methods for learning algorithms. Existing formal methods for learning and optimization primarily consider the problem of…

This paper aims to put forward the concept that learning to take safe actions in unknown environments, even with probability one guarantees, can be achieved without the need for an unbounded number of exploratory trials, provided that one…

We study data poisoning attacks in the online setting where training items arrive sequentially, and the attacker may perturb the current item to manipulate online learning. Importantly, the attacker has no knowledge of future training items…

Deep learning solutions are instrumental in cybersecurity, harnessing their ability to analyze vast datasets, identify complex patterns, and detect anomalies. However, malevolent actors can exploit these capabilities to orchestrate…

We study a regret minimization problem with the existence of multiple best/near-optimal arms in the multi-armed bandit setting. We consider the case when the number of arms/actions is comparable or much larger than the time horizon, and…

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering safety. In contrast, safe reinforcement learning seeks to reduce or avoid unsafe behavior.…

Cybersecurity is one of the most pressing technological challenges of our time and requires measures from all sectors of society. A key measure is automated security response, which enables automated mitigation and recovery from cyber…

We developed a simulation game to study the effectiveness of decision-makers in overcoming two complexities in building cybersecurity capabilities: potential delays in capability development; and uncertainties in predicting cyber incidents.…

In bandit with distribution shifts, one aims to automatically adapt to unknown changes in reward distribution, and restart exploration when necessary. While this problem has been studied for many years, a recent breakthrough of Auer et al.…

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

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…

The use of machine learning (ML) has become increasingly prevalent in various domains, highlighting the importance of understanding and ensuring its safety. One pressing concern is the vulnerability of ML applications to model stealing…

The work by Christandl, K\"onig and Renner [Phys. Rev. Lett. 102, 020504 (2009)] provides in particular the possibility of studying unconditional security in the finite-key regime for all discrete-variable protocols. We spell out this bound…

As large language models (LLMs) continue to evolve, their potential use in automating cyberattacks becomes increasingly likely. With capabilities such as reconnaissance, exploitation, and command execution, LLMs could soon become integral…

Moving target defense has emerged as a critical paradigm of protecting a vulnerable system against persistent and stealthy attacks. To protect a system, a defender proactively changes the system configurations to limit the exposure of…

Cyber-physical microgrids are vulnerable to rootkit attacks that manipulate system dynamics to create instabilities in the network. Rootkits tend to hide their access level within microgrid system components to launch sudden attacks that…

Last-iterate convergence of learning dynamics in games has attracted significant recent attention. In two-player zero-sum games with bandit feedback, where only the loss of the selected action pair is observed, Fiegel et al. (2025) show a…

Modern systems, such as digital platforms and service systems, increasingly rely on contextual bandits for online decision-making; however, their deployment can inadvertently create unfair exposure among arms, undermining long-term platform…

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…