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

Large Reasoning Models possess remarkable capabilities for self-correction in general domain; however, they frequently struggle to recover from unsafe reasoning trajectories under adversarial attacks. Existing alignment methods attempt to…

Backdoor attacks represent one of the major threats to machine learning models. Various efforts have been made to mitigate backdoors. However, existing defenses have become increasingly complex and often require high computational resources…

Decision making under uncertain environments in the maximization of expected reward while minimizing its risk is one of the ubiquitous problems in many subjects. Here, we introduce a novel problem setting in stochastic bandit optimization…

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

Black box optimisation of an unknown function from expensive and noisy evaluations is a ubiquitous problem in machine learning, academic research and industrial production. An abstraction of the problem can be formulated as a kernel based…

In this work, we highlight and perform a comprehensive study on calibration attacks, a form of adversarial attacks that aim to trap victim models to be heavily miscalibrated without altering their predicted labels, hence endangering the…

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…

Active learning methods have shown great promise in reducing the number of samples necessary for learning. As automated learning systems are adopted into real-time, real-world decision-making pipelines, it is increasingly important that…

Despite numerous countermeasures proposed by practitioners and researchers, remote control-flow alteration of programs with memory-safety vulnerabilities continues to be a realistic threat. Guaranteeing that complex software is completely…

Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an individual user is…

Information sharing is vital in resisting cyberattacks, and the volume and severity of these attacks is increasing very rapidly. Therefore responders must triage incoming warnings in deciding how to act. This study asked a very specific…

Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the…

Linear contextual bandit is a popular online learning problem. It has been mostly studied in centralized learning settings. With the surging demand of large-scale decentralized model learning, e.g., federated learning, how to retain regret…

Machine learning techniques are currently used extensively for automating various cybersecurity tasks. Most of these techniques utilize supervised learning algorithms that rely on training the algorithm to classify incoming data into…

Nowadays, cyber threats are considered among the most dangerous risks by top management of enterprises. One way to deal with these risks is to insure them, but cyber insurance is still quite expensive. The insurance fee can be reduced if…

We study security games in which a defender commits to a mixed strategy for protecting a finite set of targets of different values. An attacker, knowing the defender's strategy, chooses which target to attack and for how long. If the…

We study the stochastic multi-armed bandit problem and design new policies that enjoy both worst-case optimality for expected regret and light-tailed risk for regret distribution. Specifically, our policy design (i) enjoys the worst-case…

In this paper, we consider a best action identification problem in the stochastic linear bandit setup with a fixed confident constraint. In the considered best action identification problem, instead of minimizing the accumulative regret as…

This paper addresses the security allocation problem in a networked control system under stealthy injection attacks. The networked system is comprised of interconnected subsystems which are represented by nodes in a digraph. An adversary…

Large language models (LLMs) have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many companies provide fine-tuning API services, enabling users to…