Related papers: Symmetric Case of Locks, Bombs and Testing Model
We consider the game with discrete units of resources for protection and destruction of some sites. In our model, Defender (DF) has locks and Attacker (AT) has bombs to allocate among sites, trying to destroy these sites. One or more bombs…
Resource allocation is the process of optimizing the rare resources. In the area of security, how to allocate limited resources to protect a massive number of targets is especially challenging. This paper addresses this resource allocation…
Black-Box attacks on machine learning models occur when an attacker, despite having no access to the inner workings of a model, can successfully craft an attack by means of model theft. The attacker will train an own substitute model that…
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 study a class of optimal allocation problems, including the well-known Bomber Problem, with the following common probabilistic structure. An aircraft equipped with an amount~$x$ of ammunition is intercepted by enemy airplanes arriving…
In this paper we consider a defending problem on a network. In the model, the defender holds a total defending resource of R, which can be distributed to the nodes of the network. The defending resource allocated to a node can be shared by…
Stealthy attacks are a major cyber-security threat. In practice, both attackers and defenders have resource constraints that could limit their capabilities. Hence, to develop robust defense strategies, a promising approach is to utilize…
Advances in machine learning have led to broad deployment of systems with impressive performance on important problems. Nonetheless, these systems can be induced to make errors on data that are surprisingly similar to examples the learned…
Security Games employ game theoretical tools to derive resource allocation strategies in security domains. Recent works considered the presence of alarm systems, even suffering various forms of uncertainty, and showed that disregarding…
A variety of social, economic, and political interactions have long been modelled after Blotto games. In this paper, we introduce a general model of dynamic $n$-player Blotto contests. The players have asymmetric resources, and the…
We provide a general methodology for analyzing defender-attacker based "games" in which we model such games as Markov models and introduce a capacity region to analyze how defensive and adversarial strategies impact security. Such a…
Resource allocation problems across multiple contests are ubiquitous in adversarial settings, from military operations to market competition. While Colonel Blotto and General Lotto games have provided valuable theoretical foundations for…
We develop an analytical Stackelberg game framework for optimal resource allocation in a sequential attacker--defender setting with a finite set of assets and probabilistic attacks. The defender commits to a mixed protection strategy, after…
In this article I describe a research agenda for securing machine learning models against adversarial inputs at test time. This article does not present results but instead shares some of my thoughts about where I think that the field needs…
In classic network security games, the defender distributes defending resources to the nodes of the network, and the attacker attacks a node, with the objective to maximize the damage caused. Existing models assume that the attack at node u…
When LLMs are deployed in sensitive, human-facing settings, it is crucial that they do not output unsafe, biased, or privacy-violating outputs. For this reason, models are both trained and instructed to refuse to answer unsafe prompts such…
Machine learning models are now widely deployed in real-world applications. However, the existence of adversarial examples has been long considered a real threat to such models. While numerous defenses aiming to improve the robustness have…
LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…
Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assistance of LLMs has raised the challenge of "jailbreaking",…
There has been significant interest in studying security games for modeling the interplay of attacks and defenses on various systems involving critical infrastructure, financial system security, political campaigns, and civil safeguarding.…