Related papers: Correct-by-Construction Runtime Enforcement in AI …
While Privacy by Design (PbD) is prescribed by modern privacy regulations such as the EU's GDPR, achieving PbD in real software systems is a notoriously difficult task. One emerging technique to realize PbD is Runtime enforcement (RE), in…
AI progress is creating a growing range of risks and opportunities, but it is often unclear how they should be navigated. In many cases, the barriers and uncertainties faced are at least partly technical. Technical AI governance, referring…
There has been significant progress in sensing, perception, and localization for automated driving, However, due to the wide spectrum of traffic/road structure scenarios and the long tail distribution of human driver behavior, it has…
This article argues that frontier artificial intelligence (AI) developers need an internal audit function. First, it describes the role of internal audit in corporate governance: internal audit evaluates the adequacy and effectiveness of a…
Frontier artificial intelligence (AI) systems present both benefits and risks to society. Safety cases - structured arguments supported by evidence - are one way to help ensure the safe development and deployment of these systems. Yet the…
As machine learning models become more capable, they have exhibited increased potential in solving complex tasks. One of the most promising directions uses deep reinforcement learning to train autonomous agents in computer network defense…
Designing Reinforcement Learning (RL) solutions for real-life problems remains a significant challenge. A major area of concern is safety. "Shielding" is a popular technique to enforce safety in RL by turning user-defined safety…
In this study, we leverage the deliberate and systematic fault-injection capabilities of an open-source benchmark suite to perform a series of experiments on state-of-the-art deep and robust reinforcement learning algorithms. We aim to…
Safety is the priority concern when applying reinforcement learning (RL) algorithms to real-world control problems. While policy iteration provides a fundamental algorithm for standard RL, an analogous theoretical algorithm for safe RL…
We study automated intrusion prevention using reinforcement learning. In a novel approach, we formulate the problem of intrusion prevention as an optimal stopping problem. This formulation allows us insight into the structure of the optimal…
In the current control design of safety-critical autonomous systems, formal verification techniques are typically applied after the controller is designed to evaluate whether the required properties (e.g., safety) are satisfied. However,…
Imitation learning is a promising approach to end-to-end training of autonomous vehicle controllers. Typically the driving process with such approaches is entirely automatic and black-box, although in practice it is desirable to control the…
When AI agents retrieve and reason over external documents, adversaries can manipulate the data they receive to subvert their behaviour. Previous research has studied indirect prompt injection, where the attacker injects malicious…
This paper presents a dynamic gamification architecture for an Extended Reality Artificial Intelligence virtual training environment designed to enhance STEM education through immersive adaptive, and kinesthetic learning. The proposed…
In trigger-action IoT platforms, IoT devices report event conditions to IoT hubs notifying their cyber states and let the hubs invoke actions in other IoT devices based on functional dependencies defined as rules in a rule engine. These…
Real-time execution is essential for cyber-physical systems such as robots. These systems operate in dynamic real-world environments where even small delays can undermine responsiveness and compromise performance. Asynchronous inference has…
AI agents, specifically powered by large language models, have demonstrated exceptional capabilities in various applications where precision and efficacy are necessary. However, these agents come with inherent risks, including the potential…
Robots of the future are going to exhibit increasingly human-like and super-human intelligence in a myriad of different tasks. They are also likely going to fail and be incompliant with human preferences in increasingly subtle ways. Towards…
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…
Although AI is transforming the world, there are serious concerns about its ability to behave and make decisions responsibly. Many ethical regulations, principles, and frameworks for responsible AI have been issued recently. However, they…