相关论文: Causal Repair of Learning-enabled Cyber-physical S…

Understanding the root cause of a defect is critical to isolating and repairing buggy behavior. We present Causal Testing, a new method of root-cause analysis that relies on the theory of counterfactual causality to identify a set of…

Real-world Cyber-Physical Systems (CPSs) are usually configurable. Through parameters, it is possible to configure, select or unselect different system functionalities. While this provides high flexibility, it also becomes a source for…

Reinforcement learning (RL) algorithms often struggle to learn policies that generalize to novel situations due to issues such as causal confusion, overfitting to irrelevant factors, and failure to isolate control of state factors. These…

Causal reasoning is essential for understanding decision-making about the behaviour of complex `ecosystems' of systems that underpin modern society, with security -- including issues around correctness, safety, resilience, etc. -- typically…

Identifying the underlying reason for a failing dynamic process or otherwise anomalous observation is a fundamental challenge, yet has numerous industrial applications. Identifying the failure-causing sub-system using causal inference, one…

Mathematical models are fundamental building blocks in the design of dynamical control systems. As control systems are becoming increasingly complex and networked, approaches for obtaining such models based on first principles reach their…

This paper describes the development of a causal diagnosis approach for troubleshooting an industrial environment on the basis of the technical language expressed in Return on Experience records. The proposed method leverages the vectorized…

Behavioral cloning reduces policy learning to supervised learning by training a discriminative model to predict expert actions given observations. Such discriminative models are non-causal: the training procedure is unaware of the causal…

Large language model (LLM) agents frequently fail on multi-step tasks involving reasoning, tool use, and environment interaction. While such failures are typically logged or retried heuristically, they contain structured signals about where…

Identifying the cause of a system-level failure in a cyber-physical system (CPS) can be like tracing a needle in a haystack. This paper approaches the problem by assuming that the CPS has been designed compositionally and that each…

Learning-based methods provide a promising approach to solving highly non-linear control tasks that are often challenging for classical control methods. To ensure the satisfaction of a safety property, learning-based methods jointly learn a…

Much of our experiments are designed to uncover the cause(s) and effect(s) behind a data generating mechanism (i.e., phenomenon) we happen to be interested in. Uncovering such relationships allows us to identify the true working of a…

Identifying a causal model of an IT system is fundamental to many branches of systems engineering and operation. Such a model can be used to predict the effects of control actions, optimize operations, diagnose failures, detect intrusions,…

Online unsupervised detection of anomalies is crucial to guarantee the correct operation of cyber-physical systems and the safety of humans interacting with them. State-of-the-art approaches based on deep learning via neural networks…

Thinking in terms of causality helps us structure how different parts of a system depend on each other, and how interventions on one part of a system may result in changes to other parts. Therefore, formal models of causality are an…

Experiments remain the gold standard to establish an understanding of fire-related phenomena. A primary goal in designing tests is to uncover the data generating process (i.e., the how and why the observations we see come to be); or simply…

We study the problem of policy repair for learning-based control policies in safety-critical settings. We consider an architecture where a high-performance learning-based control policy (e.g. one trained as a neural network) is paired with…

Faithful evaluation of language model capabilities is crucial for deriving actionable insights that can inform model development. However, rigorous causal evaluations in this domain face significant methodological challenges, including…

Identifying the main features and learning the causal relationships of a dynamic system from time-series of sensor data are key problems in many real-world robot applications. In this paper, we propose an extension of a state-of-the-art…

Training control policies in simulation is more appealing than on real robots directly, as it allows for exploring diverse states in an efficient manner. Yet, robot simulators inevitably exhibit disparities from the real-world…