Related papers: Verifiability-First Agents: Provable Observability…

Manual software beta testing is costly and time-consuming, while single-agent large language model (LLM) approaches suffer from hallucinations and inconsistent behavior. We propose a multi-agent committee framework in which diverse…

We address the problem of runtime trajectory anomaly detection, a critical capability for enabling trustworthy LLM agents. Current safety measures predominantly focus on static input/output filtering. However, we argue that ensuring LLM…

In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive models to generative models and autonomous agents, the…

LLM agents process trusted instructions, retrieved records, and tool observations through a common generative channel. This conflates data flow with authority: an untrusted string can affect a secret-bearing response or an action proposal…

The evaluation of Vision-Language-Action (VLA) agents is hindered by the coarse, end-task success metric that fails to provide precise skill diagnosis or measure robustness to real-world perturbations. This challenge is exacerbated by a…

Multi-agent reinforcement learning (RL) often struggles to ensure the safe behaviours of the learning agents, and therefore it is generally not adapted to safety-critical applications. To address this issue, we present a methodology that…

The prevalent deployment of Large Language Model agents such as OpenClaw unlocks potential in real-world applications, while amplifying safety concerns. Among these concerns, the self-replication risk of LLM agents driven by objective…

Alignment audits aim to robustly identify hidden goals from strategic, situationally aware misaligned models. Despite this threat model, existing auditing methods have not been systematically stress-tested against deception strategies. We…

EASA's learning-assurance guidance requires data-driven aviation systems to build and monitor their own situation representation, yet for neural networks the technical means to provide such evidence remain an open problem. We address this…

AI agents that leverage Large Language Models (LLMs) are increasingly becoming core building blocks of modern software systems. A wide range of frameworks is now available to support the specification of such applications. These frameworks…

Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluations remain text-centric and assume that compliant language…

Grey failures in the computing continuum produce ambiguous overlapping symptoms that existing approaches fail to diagnose reliably, either due to a lack of causal awareness or acting under high epistemic uncertainty, risking destructive…

As increasingly capable large language model (LLM)-based agents are developed, the potential harms caused by misalignment and loss of control grow correspondingly severe. To address these risks, we propose an approach that directly measures…

We introduce AutoMonitor-Bench, the first benchmark designed to systematically evaluate the reliability of LLM-based misbehavior monitors across diverse tasks and failure modes. AutoMonitor-Bench consists of 3,010 carefully annotated test…

Remote run-time attestation methods, including Control Flow Attestation (CFA) and Data Flow Attestation (DFA), have been proposed to generate precise evidence of execution's control flow path (in CFA) and optionally execution data inputs…

We present an iterative algorithm for enforcing policies represented in a first-order logic, which can, in particular, express all transmission-related clauses in the HIPAA Privacy Rule. The logic has three features that raise challenges…

We propose Love First, Know Later: a paradigm shift in computational matching that simulates interactions first, then assesses compatibility. Instead of comparing static profiles, our framework leverages LLMs as text world engines that…

While reachability analysis is one of the most promising approaches for formal verification of dynamic systems, a major disadvantage preventing a more widespread application is the requirement to manually tune algorithm parameters such as…

Adversarial robustness verification is essential for ensuring the safe deployment of Large Language Models (LLMs) in runtime-critical applications. However, formal verification techniques remain computationally infeasible for modern LLMs…

Large language model (LLM) agents with extended autonomy unlock new capabilities, but also introduce heightened challenges for LLM safety. In particular, an LLM agent may pursue objectives that deviate from human values and ethical norms, a…