Related papers: Attacker Control and Impact for Confidentiality an…

We present a deductive approach for the analysis of secure information flows with support for fine-grained policies that include declassifications in the form of delimited information release. By explicitly tracking the dependencies of…

Non-interference is a popular way to enforce confidentiality of sensitive data. However, declassification of sensitive information is often needed in realistic applications but breaks non-interference. We present ANOSY, an approximate…

Information flow policies are often dynamic; the security concerns of a program will typically change during execution to reflect security-relevant events. A key challenge is how to best specify, and give proper meaning to, such dynamic…

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

The guarantees of security and privacy defenses are often strengthened by relaxing the assumptions made about attackers or the context in which defenses are deployed. Such relaxations can be a highly worthwhile topic of exploration---even…

Security of information flow is commonly understood as preventing any information leakage, regardless of how grave or harmless consequences the leakage can have. In this work, we suggest that information security is not a goal in itself,…

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees…

Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an…

Among the various means of available resource protection including biometrics, password based system is most simple, user friendly, cost effective and commonly used. But this method having high sensitivity with attacks. Most of the advanced…

The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…

Opacity is an information flow property that captures the notion of plausible deniability in dynamic systems, that is whether an intruder can deduce that "secret" behavior has occurred. In this paper we provide a general framework of…

Memory safety is traditionally characterized in terms of bad things that cannot happen. This approach is currently embraced in the literature on formal methods for memory safety. However, a general semantic principle for memory safety, that…

The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during model deployment and can evade detection by conventional…

We propose a new sheaf semantics for secure information flow over a space of abstract behaviors, based on synthetic domain theory: security classes are open/closed partitions, types are sheaves, and redaction of sensitive information…

An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images…

Machine Learning models have been shown to be vulnerable to adversarial examples, ie. the manipulation of data by a attacker to defeat a defender's classifier at test time. We present a novel probabilistic definition of adversarial examples…

The internet landscape is growing and at the same time becoming more heterogeneous. Services are performed via computers and networks, critical data is stored digitally. This enables freedom for the user, and flexibility for operators. Data…

Information leakage is becoming a critical problem as various information becomes publicly available by mistake, and machine learning models train on that data to provide services. As a result, one's private information could easily be…

In this paper, we propose an algorithm that targets contamination and eavesdropping adversaries. We consider the case when the number of independent packets available to the eavesdropper is less than the multicast capacity of the network.…

Access control systems are widely used means for the protection of computing systems. They are defined in terms of access control policies regulating the accesses to system resources. In this paper, we introduce a formally-defined,…