Related papers: Reconstructive Authority Model: Runtime Execution …
We argue that formal certification of AI alignment over open-ended or unbounded input domains is impossible under standard assumptions in computational complexity and learning theory, and characterise what remains achievable. Two…
This paper discusses the problem of estimating the state of a linear time-invariant system when some of its sensors and actuators are compromised by an adversarial agent. In the model considered in this paper, the malicious agent attacks an…
We present five results in the theory of structural governance for cognitive workflow systems. Three are mechanized in Coq 8.19 using the Interaction Trees library with parameterized coinduction; two are proved on paper with explicit…
Intermittently powered devices enable new applications in harsh or inaccessible environments, such as space or in-body implants, but also introduce problems in programmability and correctness. Researchers have developed programming models…
Reinforcement learning in partially observable environments is typically challenging, as it requires agents to learn an estimate of the underlying system state. These challenges are exacerbated in multi-agent settings, where agents learn…
Agentic AI systems produce decision evidence at scale through execution telemetry, but property-level reconstruction often fails when an external party asks a specific governance question about a specific decision: the assembled evidence is…
Agentic AI failures need post-hoc reconstruction: what the agent did, on whose authority, against which policy, and from what reasoning. Cross-regime feasibility remains unmeasured under one property-level schema. We apply the Decision…
As autonomous systems grow more advanced, objective metrics to evaluate their ethical and legal compliance are critical for informing end users of their limitations and ensuring accountability of those who misuse them. Current ethical…
This paper deals with the state estimation problem in discrete-event systems modeled with nondeterministic finite automata, partially observed via a sensor measuring unit whose measurements (reported observations) may be vitiated by a…
Autonomous agents deployed in regulated domains must produce a verification artifact per consequential output: a record an auditor can re-execute offline, capturing what was claimed, against what source, by whom, when, and how. Production…
Formal verification provides strong safety guarantees but only for models of cyber-physical systems. Hybrid system models describe the required interplay of computation and physical dynamics, which is crucial to guarantee what computations…
Given a behavior of interest in the program, statically determining the corresponding responsible entity is a task of critical importance, especially in program security. Classical static analysis techniques (e.g. dependency analysis, taint…
In this paper, a constrained attack-resilient estimation algorithm (CARE) is developed for stochastic cyber-physical systems. The proposed CARE can simultaneously estimate the compromised system states and attack signals. It has improved…
We consider the problem of safe control in discrete autonomous agents that use learned components for imperfect perception (or more generally, state estimation) from high-dimensional observations. We propose a shield construction that…
Agentic AI systems plan, use tools, maintain state, and act across multi-step workflows with external effects, meaning trustworthy deployment can no longer be judged by task completion alone. The current literature remains fragmented across…
We consider the problem of estimating the state of a linear Gaussian system in the presence of integrity attacks. The attacker can compromise $p$ out of $m$ sensors, the set of which is fixed and unknown to the system operator, and…
Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer…
Event-driven scheduling policies are increasingly deployed in industrial environments, where decisions are made under asynchronous and partially observed system states. As a result, decision states are not temporally consistent, action…
Universal QRAM (U-QRAM) is a fixed, data-independent unitary interface that implements coherent random-access reads relative to a designated computational "truth-table" basis on the memory register. This work studies restricted-access…
Reliable reward models (RMs) are critical for ensuring the safe alignment of large language models (LLMs). However, current RM evaluation methods focus solely on preference perception accuracies in given specific scenarios, obscuring the…