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

While ideal quantum key distribution (QKD) systems are well-understood, practical implementations face various vulnerabilities, such as side-channel attacks resulting from device imperfections. Current security proofs for decoy-state BB84…

Motivated by safety-critical classification problems, we investigate adversarial attacks against cost-sensitive classifiers. We use current state-of-the-art adversarially-resistant neural network classifiers [1] as the underlying models.…

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…

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

As LLMs develop increasingly advanced capabilities, there is an increased need to minimize the harm that could be caused to society by certain model outputs; hence, most LLMs have safety guardrails added, for example via fine-tuning. In…

Most existing works focus on direct perturbations to the victim's state/action or the underlying transition dynamics to demonstrate the vulnerability of reinforcement learning agents to adversarial attacks. However, such direct…

A plethora of jailbreaking attacks have been proposed to obtain harmful responses from safety-tuned LLMs. These methods largely succeed in coercing the target output in their original settings, but their attacks vary substantially in…

The susceptibility of deep learning models to adversarial perturbations has stirred renewed attention in adversarial examples resulting in a number of attacks. However, most of these attacks fail to encompass a large spectrum of adversarial…

There are two main attack models considered in the adversarial robustness literature: black-box and white-box. We consider these threat models as two ends of a fine-grained spectrum, indexed by the number of queries the adversary can ask.…

This paper proposes a variant of multiple-play stochastic bandits tailored to resource allocation problems arising from LLM applications, edge intelligence, etc. The model is composed of $M$ arms and $K$ plays. Each arm has a stochastic…

A symmetric device-independent quantum key distribution (DIQKD) protocol is proposed in this paper, with Holevo limit and subadditivity of von Neumann entropy, one can bound Eve's ability with collective attack. Together with symmetry of…

Despite extensive safety measures, LLMs are vulnerable to adversarial inputs, or jailbreaks, which can elicit unsafe behaviors. In this work, we introduce bijection learning, a powerful attack algorithm which automatically fuzzes LLMs for…

Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text. However, with their rising prominence, the…

We explore a scenario involving two sites and a sequential game between a defender and an attacker, where the defender is responsible for securing the sites while the attacker aims to attack them. Each site holds a loss value for the…

The problem of adversarial examples, evasion attacks on machine learning classifiers, has proven extremely difficult to solve. This is true even when, as is the case in many practical settings, the classifier is hosted as a remote service…

We introduce a defense against adversarial attacks on LLMs utilizing self-evaluation. Our method requires no model fine-tuning, instead using pre-trained models to evaluate the inputs and outputs of a generator model, significantly reducing…

Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe outputs. In this paper, we introduce and evaluate a new…

Recent study of adversarial attacks has revealed the vulnerability of modern deep learning models. That is, subtly crafted perturbations of the input can make a trained network with high accuracy produce arbitrary incorrect predictions,…

As the development of large language models (LLMs) rapidly advances, securing these models effectively without compromising their utility has become a pivotal area of research. However, current defense strategies against jailbreak attacks…

We consider a stochastic version of the well-known Blotto game, called the gladiator game. In this zero-sum allocation game two teams of gladiators engage in a sequence of one-to-one fights in which the probability of winning is a function…