Related papers: If it's Provably Secure, It Probably Isn't: Why Le…

This paper consists of musings that originate mainly from conversations with other physicists, as together we've tried to learn some cryptography, but also from conversations with a couple of classical cryptographers. The main thrust of the…

Certified defenses promise provable robustness guarantees. We study the malicious exploitation of probabilistic certification frameworks to better understand the limits of guarantee provisions. Now, the objective is to not only mislead a…

There are plenty of security software in market; each claiming the best, still we daily face problem of viruses and other malicious activities. If we know the basic working principal of such malware then we can very easily prevent most of…

As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels. In addition to eliminating the need for labeled data, research has found…

SAML assertions are becoming popular method for passing authentication and authorisation information between identity providers and consumers using various single sign-on protocols. However their practical security strongly depends on…

In recent times, many protocols have been proposed to provide security for various information and communication systems. Such protocols must be tested for their functional correctness before they are used in practice. Application of formal…

Self-Supervised Learning (SSL) is crucial for real-world applications, especially in data-hungry domains such as healthcare and self-driving cars. In addition to a lack of labeled data, these applications also suffer from distributional…

Physical implementations of cryptographic algorithms leak information, which makes them vulnerable to so-called side-channel attacks. The problem of secure computation in the presence of leakage is generally known as leakage resilience. In…

Self-Supervised Learning (SSL) has shown great promise in learning representations from unlabeled data. The power of learning representations without the need for human annotations has made SSL a widely used technique in real-world…

Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulnerable to human…

In this work we investigate the problem of simultaneous privacy and integrity protection in cryptographic circuits. We consider a white-box scenario with a powerful, yet limited attacker. A concise metric for the level of probing and fault…

Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…

Protecting secrets is a key challenge in our contemporary information-based era. In common situations, however, revealing secrets appears unavoidable, for instance, when identifying oneself in a bank to retrieve money. In turn, this may…

Translucency is now a common design element in at least one popular mobile operating system. This raises security concerns as it can make it harder for users to correctly identify and interpret trusted interaction elements. In this paper,…

Justifying the correct implementation of the non-functional requirements (e.g., safety, security) of mission-critical systems is crucial to prevent system failure. The later could have severe consequences such as the death of people and…

We consider the problem of how to verify the security of probabilistic oblivious algorithms formally and systematically. Unfortunately, prior program logics fail to support a number of complexities that feature in the semantics and…

In this paper, we propose the use of interactive theorem proving for explainable machine learning. After presenting our proposition, we illustrate it on the dedicated application of explaining security attacks using the Isabelle…

At IEEE S&P 2019, the paper "DeepSec: A Uniform Platform for Security Analysis of Deep Learning Model" aims to to "systematically evaluate the existing adversarial attack and defense methods." While the paper's goals are laudable, it fails…

Experimental research methods describe standards to safeguard scientific integrity and reputability. These methods have been extensively integrated into traditional scientific disciplines and studied in the philosophy of science. The field…

Effective software safety standards will contribute to confidence, or assurance, in the safety of the systems in which the software is used. It is infeasible to demonstrate a correlation between standards and accidents, but there is an…