Related papers: Symmetric Case of Locks, Bombs and Testing Model

We consider a path guarding problem in dynamic Defender-Attacker Blotto games (dDAB), where a team of robots must defend a path in a graph against adversarial agents. Multi-robot systems are particularly well suited to this application, as…

We consider the problem of optimally allocating a given total storage budget in a distributed storage system. A source has a data object which it can code and store over a set of storage nodes; it is allowed to store any amount of coded…

Cryptocurrencies have garnered much attention in recent years, both from the academic community and industry. One interesting aspect of cryptocurrencies is their explicit consideration of incentives at the protocol level. Understanding how…

In this paper, we consider a new network security game wherein an attacker and a defender are battling over "multiple" targets. This type of game is appropriate to model many current network security conflicts such as Internet phishing,…

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a…

Large language models (LLMs) undergo safety alignment after training and tuning, yet recent work shows that safety can be bypassed through jailbreak attacks. While many jailbreaks and defenses exist, their cross-lingual generalization…

Advanced Persistent Threat (APT) attackers apply multiple sophisticated methods to continuously and stealthily steal information from the targeted cloud storage systems and can even induce the storage system to apply a specific defense…

Existing studies in backdoor defense have predominantly focused on the training phase, overlooking the critical aspect of testing time defense. This gap becomes pronounced in the context of LLMs deployed as Web Services, which typically…

Large language models (LLMs) are vital for a wide range of applications yet remain susceptible to jailbreak threats, which could lead to the generation of inappropriate responses. Conventional defenses, such as refusal and adversarial…

Large language models (LLMs), known for their capability in understanding and following instructions, are vulnerable to adversarial attacks. Researchers have found that current commercial LLMs either fail to be "harmless" by presenting…

As large language models grow increasingly capable, concerns about their safe deployment have intensified. While numerous alignment strategies aim to restrict harmful behavior, these defenses can still be circumvented through carefully…

We consider the problem of sequentially allocating resources in a censored semi-bandits setup, where the learner allocates resources at each step to the arms and observes loss. The loss depends on two hidden parameters, one specific to the…

This paper studies a stochastic game theoretic approach to security and intrusion detection in communication and computer networks. Specifically, an Attacker and a Defender take part in a two-player game over a network of nodes whose…

Finite mixtures of classifiers (a.k.a. randomized ensembles) have been proposed as a way to improve robustness against adversarial attacks. However, existing attacks have been shown to not suit this kind of classifier. In this paper, we…

Colonel Blotto games with discrete strategy spaces effectively illustrate the intricate nature of multidimensional strategic reasoning. This paper studies the equilibrium set of such games where, in line with prior experimental work, the…

It is becoming increasingly imperative to design robust ML defenses. However, recent work has found that many defenses that initially resist state-of-the-art attacks can be broken by an adaptive adversary. In this work we take steps to…

Collaborative multi-agent reinforcement learning has rapidly evolved, offering state-of-the-art algorithms for real-world applications, including sensitive domains. However, a key challenge to its widespread adoption is the lack of a…

The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval. However, these systems are vulnerable to adversarial attacks, especially ranking manipulation attacks,…

We introduce the {Destructive Object Handling} (DOH) problem, which models aspects of many real-world allocation problems, such as shipping explosive munitions, scheduling processes in a cluster with fragile nodes, re-using passwords across…

Jailbreak attacks, where harmful prompts bypass generative models' built-in safety, raise serious concerns about model vulnerability. While many defense methods have been proposed, the trade-offs between safety and helpfulness, and their…