Related papers: Shields to Guarantee Probabilistic Safety in MDPs

Cyber-physical systems are often safety-critical in that violations of safety properties may lead to catastrophes. We propose a method to enforce the safety of systems with real-valued signals by synthesizing a runtime enforcer called the…

Privacy Shielding against Mass Surveillance provides a step by step tactical approach to protecting the privacy of all the users of the internet from mass surveillance programs by the governments and other state agencies. Protection of…

Continued adoption of agricultural robots postulates the farmer's trust in the reliability, robustness and safety of the new technology. This motivates our work on safety assurance of agricultural robots, particularly their ability to…

Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed…

Partially observable Markov decision processes (POMDPs) provide a modeling framework for a variety of sequential decision making under uncertainty scenarios in artificial intelligence (AI). Since the states are not directly observable in a…

Cascading failures, triggered by a local perturbation, can be catastrophic and cause irreparable damages in a wide area. Hence, blocking the devastating cascades is an important issue in real world networks. One of the ways to control the…

Recent advances in reinforcement learning (RL) enable its use on increasingly complex tasks, but the lack of formal safety guarantees still limits its application in safety-critical settings. A common practical approach is to augment the RL…

Cyber-physical systems (CPS) can be found everywhere: smart homes, autonomous vehicles, aircrafts, healthcare, agriculture and industrial production lines. CPSs are often critical, as system failure can cause serious damage to property and…

Multi-agent partially observable Markov decision processes (MPOMDPs) provide a framework to represent heterogeneous autonomous agents subject to uncertainty and partial observation. In this paper, given a nominal policy provided by a human…

Autonomous agents powered by foundation models have seen widespread adoption across various real-world applications. However, they remain highly vulnerable to malicious instructions and attacks, which can result in severe consequences such…

We propose novel controller synthesis techniques for probabilistic systems modelled using stochastic two-player games: one player acts as a controller, the second represents its environment, and probability is used to capture uncertainty…

Secure Multi-Party Computation (MPC) is an important enabling technology for data privacy in modern distributed applications. Currently, proof methods for low-level MPC protocols are primarily manual and thus tedious and error-prone, and…

This position paper argues that enforcing LLM agent safety within a single abstraction layer is not merely suboptimal but categorically insufficient for deployed LLM agents -- a structural consequence of how agent execution works, not a…

Qualitative opacity of a secret is a security property, which means that a system trajectory satisfying the secret is observation-equivalent to a trajectory violating the secret. In this paper, we study how to synthesize a control policy…

This report presents a structured Robotics Physical Safety Framework based on explicit asset declaration, systematic vulnerability enumeration, and hazard-driven synthetic data generation. The approach bridges classical risk engineering…

While learning-based control techniques often outperform classical controller designs, safety requirements limit the acceptance of such methods in many applications. Recent developments address this issue through so-called predictive safety…

Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…

A shield is attached to a system to guarantee safety by correcting the system's behavior at runtime. Existing methods that employ design-time synthesis of shields do not scale to multi-agent systems. Moreover, such shields are typically…

The Differentially Private Stochastic Gradient Descent (DP-SGD) algorithm supports the training of machine learning (ML) models with formal Differential Privacy (DP) guarantees. Traditionally, DP-SGD processes training data in batches using…

System assurance is confronted by significant challenges. Some of these are new, for example, autonomous systems with major functions driven by machine learning and AI, and ultra-rapid system development, while others are the familiar,…