Related papers: Verifying Policy Enforcers
Agentic AI systems execute a sequence of actions, such as reasoning steps or tool calls, in response to a user prompt. To evaluate the success of their trajectories, researchers have developed verifiers, such as LLM judges and…
Multi-Agent Systems (MAS) are notoriously complex and hard to verify. In fact, it is not trivial to model a MAS, and even when a model is built, it is not always possible to verify, in a formal way, that it is actually behaving as we…
Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once granted execution authority, the central challenge becomes how to keep actions governable at…
Online websites use cookie notices to elicit consent from the users, as required by recent privacy regulations like the GDPR and the CCPA. Prior work has shown that these notices use dark patterns to manipulate users into making…
Like many desktop operating systems in the 1990s, Android is now in the process of including support for multi-user scenarios. Because these scenarios introduce new threats to the system, we should have an understanding of how well the…
Existing methods for verifying access control policies require the policy to be complete and fully determined before verification can proceed, but in practice policies are developed iteratively, composed from independently maintained…
Mobile phones have developed into complex platforms with large numbers of installed applications and a wide range of sensitive data. Application security policies limit the permissions of each installed application. As applications may…
Modern web applications serve large amounts of sensitive user data, access to which is typically governed by data-access policies. Enforcing such policies is crucial to preventing improper data access, and prior work has proposed many…
With the advent of wide security platforms able to express simultaneously all the policies comprising an organization's global security policy, the problem of inconsistencies within security policies become harder and more relevant. We have…
Access control policies are used to restrict access to sensitive records for authorized users only. One approach for specifying policies is using role based access control (RBAC) where authorization is given to roles instead of users. Users…
During the development of the security subsystem of modern information systems, a problem of the joint implementation of several access control models arises quite often. Traditionally, a request for the user's access to resources is…
The sustained popularity of the cloud and cloud-related services accelerate the evolution of virtualization-enabling technologies. Modern off-the-shelf computers are already equipped with specialized hardware that enables a hypervisor to…
System integration testing is the process of testing a system by the stepwise integration of sub-components. Usually these sub-components are already verified to guarantee their correct functional behavior. By integration of these verified…
Cache coherence protocols based on self-invalidation and self-downgrade have recently seen increased popularity due to their simplicity, potential performance efficiency, and low energy consumption. However, such protocols result in memory…
Automated Vehicles require exhaustive testing in simulation to detect as many safety-critical failures as possible before deployment on public roads. In this work, we focus on the core decision-making component of autonomous robots: their…
Option discovery and skill acquisition frameworks are integral to the functioning of a Hierarchically organized Reinforcement learning agent. However, such techniques often yield a large number of options or skills, which can potentially be…
As autonomous agents become more powerful and widely used, it is becoming increasingly important to ensure they behave safely and stay aligned with system goals, especially in multi-agent settings. Current systems often rely on agents…
Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the…
As an information-flow privacy property, opacity characterizes whether a malicious external observer (referred to as an intruder) is able to infer the secret behavior of a system. This paper addresses the problem of opacity enforcement…
In the area of networks, a common method to enforce a security policy expressed in a high-level language is based on an ad-hoc and manual rewriting process. We argue that it is possible to build a formal link between concrete and abstract…