Related papers: Modeling Adversaries in a Logic for Security Proto…

In security protocol analysis, the traditional choice to consider a single Dolev-Yao attacker is supported by the fact that models with multiple collaborating Dolev-Yao attackers have been shown to be reducible to models with one Dolev-Yao…

Reasoning about security properties involves reasoning about where the information of a system is located, and how it evolves over time. While most security analysis techniques need to cope with some notions of information locality and…

Security protocols are often found to be flawed after their deployment. We present an approach that aims at the neutralization or mitigation of the attacks to flawed protocols: it avoids the complete dismissal of the interested protocol and…

Memory erasure protocols serve to clean up a device's memory before the installation of new software. Although this task can be accomplished by direct hardware manipulation, remote software-based memory erasure protocols have emerged as a…

In this paper we propose a general definition of secrecy for cryptographic protocols in the Dolev-Yao model. We give a sufficient condition ensuring secrecy for protocols where rules have encryption depth at most two, that is satisfied by…

We propose extensions to the Dolev-Yao attacker model to make it suitable for arguments about security of Cyber-Physical Systems. The Dolev-Yao attacker model uses a set of rules to define potential actions by an attacker with respect to…

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial…

Current formal verification of security protocols relies on specialized researchers and complex tools, inaccessible to protocol designers who informally evaluate their work with emulators. This paper addresses this gap by embedding symbolic…

The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same…

Classification problems in security settings are usually contemplated as confrontations in which one or more adversaries try to fool a classifier to obtain a benefit. Most approaches to such adversarial classification problems have focused…

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…

Despite the recent advances in a wide spectrum of applications, machine learning models, especially deep neural networks, have been shown to be vulnerable to adversarial attacks. Attackers add carefully-crafted perturbations to input, where…

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings…

Classical symbolic protocol verification under Dolev--Yao uses binary attacker knowledge (known/unknown). This abstraction misses cumulative side-channel settings, where repeated noisy observations progressively improve attacker knowledge.…

Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…

Given the widespread use of deep learning models in safety-critical applications, ensuring that the decisions of such models are robust against adversarial exploitation is of fundamental importance. In this thesis, we discuss recent…

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…

The design of the defenses Internet systems can deploy against attack, especially adaptive and resilient defenses, must start from a realistic model of the threat. This requires an assessment of the capabilities of the adversary. The design…

Though deep neural networks have achieved state-of-the-art performance in visual classification, recent studies have shown that they are all vulnerable to the attack of adversarial examples. Small and often imperceptible perturbations to…