arXiv subjects

Kim Hammar

Publications and source records attributed to Kim Hammar.

At least 19 recordsLinked to original sources

arXiv2026

Optimal Stopping of Self-Refining Foundation Models

Foundation models can improve their outputs through a self-refinement process driven by external feedback. In this process, the model is embedded in an iterative loop where it generates outputs, receives feedback from verifiers, and refines its responses through in-context learning. Following a novel approach, we formalize this process as an optimal stopping problem where the number of refinement iterations is decided based on expected improvement relative to cost. We derive optimal stopping policies and show that they can be efficiently computed through stochastic approximation. To evaluate our approach experimentally, we apply it to a coding benchmark for foundation models. The empirical results show that our stopping policies are significantly more cost-efficient than stopping policies proposed in prior work.

eess.SY↗

arXiv2026

Agentic Incident Response through Digital Twin-Enhanced Multiscale Planning

Incident response is currently managed by security operators using predefined playbooks, resulting in slow, labor-intensive security decision-making processes. Consequently, there is a growing need for automated incident response planning. Decision-theoretic approaches based on control, optimization, and reinforcement learning have been proposed to automate such planning tasks with well-grounded approaches, yet most of which, while guaranteeing strong performance, are limited to abstract models and cannot be directly applied to operational systems. A promising approach to mitigate this limitation is to use the security knowledge embedded in large language models (LLMs) to develop agentic response systems. However, current agentic approaches rely on repeated invocations of the LLM to generate a response plan, which is unreliable and limits the planning horizon due to hallucination. In this paper, we develop a principled LLM-based planning method by combining decision-theoretic planning with LLM-generated response commands. The proposed agentic incident response approach uses a rollout planner to compute a high-level response strategy that allocates security resources (the tactical scale), which is then translated into executable commands by a lightweight LLM agent (the operational scale). Within this architecture, we use a digital twin that supports tactical planning through simulation and operational execution through emulation. Across three attack scenarios, our agentic approach reduces recovery execution time by 15.1\% on average and increases the recovery rate by 33.6\% over frontier LLM baselines.

cs.CR↗

arXiv2026

Recovery Control in Replicated Systems through Autonomous Multiagent Rollout

We study recovery control in replicated computing systems. Such systems consist of replicas that collectively provide a service to a client population. This redundancy enables the system to withstand failures provided that failed replicas are recovered faster than new failures occur. We show that the problem of deciding when to initiate recovery of selected replicas can be formulated as a partially observable Markov decision problem (POMDP) with a multiagent structure. We exploit this structure to apply a multiagent rollout method for approximating optimal control policies. Our method uses precomputed signaling information that reduces the need for replica coordination and facilitates parallel computations. Experiments show that our method scales to systems with up to 70 replicas and reduces costs compared to the recovery policies currently used in practice.

eess.SY↗

arXiv2026

CSLE: A Reinforcement Learning Platform for Autonomous Security Management

Reinforcement learning is a promising approach to autonomous and adaptive security management in networked systems. However, current reinforcement learning solutions for security management are mostly limited to simulation environments and it is unclear how they generalize to operational systems. In this paper, we address this limitation by presenting CSLE: a reinforcement learning platform for autonomous security management that enables experimentation under realistic conditions. Conceptually, CSLE encompasses two systems. First, it includes an emulation system that replicates key components of the target system in a virtualized environment. We use this system to gather measurements and logs, based on which we identify a system model, such as a Markov decision process. Second, it includes a simulation system where security strategies are efficiently learned through simulations of the system model. The learned strategies are then evaluated and refined in the emulation system to close the gap between theoretical and operational performance. We demonstrate CSLE through four use cases: flow control, replication control, segmentation control, and recovery control. Through these use cases, we show that CSLE enables near-optimal security management in an environment that approximates an operational system.

cs.CR↗

arXiv2026

In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach

Rapidly evolving cyberattacks demand incident response systems that can autonomously learn and adapt to changing threats. Prior work has extensively explored the reinforcement learning approach, which involves learning response strategies through extensive simulation of the incident. While this approach can be effective, it requires handcrafted modeling of the simulator and suppresses useful semantics from raw system logs and alerts. To address these limitations, we propose to leverage large language models' (LLM) pre-trained security knowledge and in-context learning to create an end-to-end agentic solution for incident response planning. Specifically, our agent integrates four functionalities, perception, reasoning, planning, and action, into one lightweight LLM (14b model). Through fine-tuning and chain-of-thought reasoning, our LLM agent is capable of processing system logs and inferring the underlying network state (perception), updating its conjecture of attack models (reasoning), simulating consequences under different response strategies (planning), and generating an effective response (action). By comparing LLM-simulated outcomes with actual observations, the LLM agent repeatedly refines its attack conjecture and corresponding response, thereby demonstrating in-context adaptation. Our agentic approach is free of modeling and can run on commodity hardware. When evaluated on incident logs reported in the literature, our agent achieves recovery up to 23% faster than those of frontier LLMs.

cs.CR↗

arXiv2026

Hallucination-Resistant Security Planning with a Large Language Model

Large language models (LLMs) are promising tools for supporting security management tasks, such as incident response planning. However, their unreliability and tendency to hallucinate remain significant challenges. In this paper, we address these challenges by introducing a principled framework for using an LLM as decision support in security management. Our framework integrates the LLM in an iterative loop where it generates candidate actions that are checked for consistency with system constraints and lookahead predictions. When consistency is low, we abstain from the generated actions and instead collect external feedback, e.g., by evaluating actions in a digital twin. This feedback is then used to refine the candidate actions through in-context learning (ICL). We prove that this design allows to control the hallucination risk by tuning the consistency threshold. Moreover, we establish a bound on the regret of ICL under certain assumptions. To evaluate our framework, we apply it to an incident response use case where the goal is to generate a response and recovery plan based on system logs. Experiments on four public datasets show that our framework reduces recovery times by up to 30% compared to frontier LLMs.

cs.AI↗

arXiv2026

Causal Online Learning of Safe Regions in Cloud Radio Access Networks

Cloud radio access networks (RANs) enable cost-effective management of mobile networks by dynamically scaling their capacity on demand. However, deploying adaptive controllers to implement such dynamic scaling in operational networks is challenging due to the risk of breaching service agreements and operational constraints. To mitigate this challenge, we present a novel method for learning the safe operating region of the RAN, i.e., the set of resource allocations and network configurations for which its specification is fulfilled. The method, which we call (C)ausal (O)nline (L)earning, operates in two online phases: an inference phase and an intervention phase. In the first phase, we passively observe the RAN to infer an initial safe region via causal inference and Gaussian process regression. In the second phase, we gradually expand this region through interventional Bayesian learning. We prove that COL ensures that the learned region is safe with a specified probability and that it converges to the full safe region under standard conditions. We experimentally validate COL on a 5G testbed. The results show that COL quickly learns the safe region while incurring low operational cost and being up to 10x more sample-efficient than current state-of-the-art methods for safe learning.

cs.NI↗

arXiv2025

Online Identification of IT Systems through Active Causal Learning

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, etc., which is central to achieving the longstanding goal of automating network and system management tasks. Traditionally, causal models have been designed and maintained by domain experts. This, however, proves increasingly challenging with the growing complexity and dynamism of modern IT systems. In this paper, we present the first principled method for online, data-driven identification of an IT system in the form of a causal model. The method, which we call active causal learning, estimates causal functions that capture the dependencies among system variables in an iterative fashion using Gaussian process regression based on system measurements, which are collected through a rollout-based intervention policy. We prove that this method is optimal in the Bayesian sense and that it produces effective interventions. Experimental validation on a testbed shows that our method enables accurate identification of a causal system model while inducing low interference with system operations.

cs.LG↗

arXiv2025

Online Incident Response Planning under Model Misspecification through Bayesian Learning and Belief Quantization

Effective responses to cyberattacks require fast decisions, even when information about the attack is incomplete or inaccurate. However, most decision-support frameworks for incident response rely on a detailed system model that describes the incident, which restricts their practical utility. In this paper, we address this limitation and present an online method for incident response planning under model misspecification, which we call MOBAL: Misspecified Online Bayesian Learning. MOBAL iteratively refines a conjecture about the model through Bayesian learning as new information becomes available, which facilitates model adaptation as the incident unfolds. To determine effective responses online, we quantize the conjectured model into a finite Markov model, which enables efficient response planning through dynamic programming. We prove that Bayesian learning is asymptotically consistent with respect to the information feedback. Additionally, we establish bounds on misspecification and quantization errors. Experiments on the CAGE-2 benchmark show that MOBAL outperforms the state of the art in terms of adaptability and robustness to model misspecification.

cs.LG↗

arXiv2025

Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination

Timely and effective incident response is key to managing the growing frequency of cyberattacks. However, identifying the right response actions for complex systems is a major technical challenge. A promising approach to mitigate this challenge is to use the security knowledge embedded in large language models (LLMs) to assist security operators during incident handling. Recent research has demonstrated the potential of this approach, but current methods are mainly based on prompt engineering of frontier LLMs, which is costly and prone to hallucinations. We address these limitations by presenting a novel way to use an LLM for incident response planning with reduced hallucination. Our method includes three steps: fine-tuning, information retrieval, and lookahead planning. We prove that our method generates response plans with a bounded probability of hallucination and that this probability can be made arbitrarily small at the expense of increased planning time under certain assumptions. Moreover, we show that our method is lightweight and can run on commodity hardware. We evaluate our method on logs from incidents reported in the literature. The experimental results show that our method a) achieves up to 22% shorter recovery times than frontier LLMs and b) generalizes to a broad range of incident types and response actions.

cs.CR↗

arXiv2025

Adaptive Network Security Policies via Belief Aggregation and Rollout

Evolving security vulnerabilities and shifting operational conditions require frequent updates to network security policies. These updates include adjustments to incident response procedures and modifications to access controls, among others. Reinforcement learning methods have been proposed for automating such policy adaptations, but most methods in the research literature lack performance guarantees and adapt slowly to changes. In this paper, we address these limitations and present a method for computing security policies that is scalable, offers theoretical guarantees, and adapts quickly to changes. The method uses a model or simulator of the system, which is updated when changes occur, and combines three components: belief estimation through particle filtering, offline policy computation through feature-based aggregation, and online policy adaptation through rollout. In particular, feature-based aggregation enables scalable offline optimization of a policy, while rollout adapts the policy online to changes in the system model without repeating the offline optimization. We analyze the approximation error of the aggregation and show that the rollout efficiently adapts policies to changes under certain conditions. Simulations and testbed results demonstrate that our method outperforms state-of-the-art methods on several benchmarks, including CAGE-2.

eess.SY↗

arXiv2025

Feature-Based Belief Aggregation for Partially Observable Markov Decision Problems

We consider a finite-state partially observable Markov decision problem (POMDP) with an infinite horizon and a discounted cost, and we propose a new method for computing a cost function approximation that is based on features and aggregation. In particular, using the classical belief-space formulation, we construct a related Markov decision problem (MDP) by first aggregating the unobservable states into feature states, and then introducing representative beliefs over these feature states. This two-stage aggregation approach facilitates the use of dynamic programming methods for solving the aggregate problem and provides additional design flexibility. The optimal cost function of the aggregate problem can in turn be used within an on-line approximation in value space scheme for the original POMDP. We derive a new bound on the approximation error of our scheme. In addition, we establish conditions under which the cost function approximation provides a lower bound for the optimal cost. Finally, we present a biased aggregation approach, which leverages an optimal cost function estimate to improve the quality of the approximation error of the aggregate problem.

eess.SY↗

arXiv2025

Optimal Security Response to Network Intrusions in IT Systems

Cybersecurity is one of the most pressing technological challenges of our time and requires measures from all sectors of society. A key measure is automated security response, which enables automated mitigation and recovery from cyber attacks. Significant strides toward such automation have been made due to the development of rule-based response systems. However, these systems have a critical drawback: they depend on domain experts to configure the rules, a process that is both error-prone and inefficient. Framing security response as an optimal control problem shows promise in addressing this limitation but introduces new challenges. Chief among them is bridging the gap between theoretical optimality and operational performance. Current response systems with theoretical optimality guarantees have only been validated analytically or in simulation, leaving their practical utility unproven. This thesis tackles the aforementioned challenges by developing a practical methodology for optimal security response in IT infrastructures. It encompasses two systems. First, it includes an emulation system that replicates key components of the target infrastructure. We use this system to gather measurements and logs, based on which we identify a game-theoretic model. Second, it includes a simulation system where game-theoretic response strategies are optimized through stochastic approximation to meet a given objective, such as mitigating potential attacks while maintaining operational services. These strategies are then evaluated and refined in the emulation system to close the gap between theoretical and operational performance. We prove structural properties of optimal response strategies and derive efficient algorithms for computing them. This enables us to solve a previously unsolved problem: demonstrating optimal security response against network intrusions on an IT infrastructure.

cs.GT↗

arXiv2024

Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search

The CAGE-2 challenge is considered a standard benchmark to compare methods for autonomous cyber defense. Current state-of-the-art methods evaluated against this benchmark are based on model-free (offline) reinforcement learning, which does not provide provably optimal defender strategies. We address this limitation and present a formal (causal) model of CAGE-2 together with a method that produces a provably optimal defender strategy, which we call Causal Partially Observable Monte-Carlo Planning (C-POMCP). It has two key properties. First, it incorporates the causal structure of the target system, i.e., the causal relationships among the system variables. This structure allows for a significant reduction of the search space of defender strategies. Second, it is an online method that updates the defender strategy at each time step via tree search. Evaluations against the CAGE-2 benchmark show that C-POMCP achieves state-of-the-art performance with respect to effectiveness and is two orders of magnitude more efficient in computing time than the closest competitor method.

cs.LG↗

arXiv2024

Intrusion Tolerance for Networked Systems through Two-Level Feedback Control

We formulate intrusion tolerance for a system with service replicas as a two-level optimal control problem. On the local level node controllers perform intrusion recovery, and on the global level a system controller manages the replication factor. The local and global control problems can be formulated as classical problems in operations research, namely, the machine replacement problem and the inventory replenishment problem. Based on this formulation, we design TOLERANCE, a novel control architecture for intrusion-tolerant systems. We prove that the optimal control strategies on both levels have threshold structure and design efficient algorithms for computing them. We implement and evaluate TOLERANCE in an emulation environment where we run 10 types of network intrusions. The results show that TOLERANCE can improve service availability and reduce operational cost compared with state-of-the-art intrusion-tolerant systems.

cs.DC↗

arXiv2024

Conjectural Online Learning with First-order Beliefs in Asymmetric Information Stochastic Games

Asymmetric information stochastic games (AISGs) arise in many complex socio-technical systems, such as cyber-physical systems and IT infrastructures. Existing computational methods for AISGs are primarily offline and can not adapt to equilibrium deviations. Further, current methods are limited to particular information structures to avoid belief hierarchies. Considering these limitations, we propose conjectural online learning (COL), an online learning method under generic information structures in AISGs. COL uses a forecaster-actor-critic (FAC) architecture, where subjective forecasts are used to conjecture the opponents' strategies within a lookahead horizon, and Bayesian learning is used to calibrate the conjectures. To adapt strategies to nonstationary environments based on information feedback, COL uses online rollout with cost function approximation (actor-critic). We prove that the conjectures produced by COL are asymptotically consistent with the information feedback in the sense of a relaxed Bayesian consistency. We also prove that the empirical strategy profile induced by COL converges to the Berk-Nash equilibrium, a solution concept characterizing rationality under subjectivity. Experimental results from an intrusion response use case demonstrate COL's {faster convergence} over state-of-the-art reinforcement learning methods against nonstationary attacks.

cs.GT↗

arXiv2024

Automated Security Response through Online Learning with Adaptive Conjectures

We study automated security response for an IT infrastructure and formulate the interaction between an attacker and a defender as a partially observed, non-stationary game. We relax the standard assumption that the game model is correctly specified and consider that each player has a probabilistic conjecture about the model, which may be misspecified in the sense that the true model has probability 0. This formulation allows us to capture uncertainty and misconception about the infrastructure and the intents of the players. To learn effective game strategies online, we design Conjectural Online Learning (COL), a novel method where a player iteratively adapts its conjecture using Bayesian learning and updates its strategy through rollout. We prove that the conjectures converge to best fits, and we provide a bound on the performance improvement that rollout enables with a conjectured model. To characterize the steady state of the game, we propose a variant of the Berk-Nash equilibrium. We present COL through an advanced persistent threat use case. Testbed evaluations show that COL produces effective security strategies that adapt to a changing environment. We also find that COL enables faster convergence than current reinforcement learning techniques.

cs.GT↗

arXiv2023

Scalable Learning of Intrusion Responses through Recursive Decomposition

We study automated intrusion response for an IT infrastructure and formulate the interaction between an attacker and a defender as a partially observed stochastic game. To solve the game we follow an approach where attack and defense strategies co-evolve through reinforcement learning and self-play toward an equilibrium. Solutions proposed in previous work prove the feasibility of this approach for small infrastructures but do not scale to realistic scenarios due to the exponential growth in computational complexity with the infrastructure size. We address this problem by introducing a method that recursively decomposes the game into subgames which can be solved in parallel. Applying optimal stopping theory we show that the best response strategies in these subgames exhibit threshold structures, which allows us to compute them efficiently. To solve the decomposed game we introduce an algorithm called Decompositional Fictitious Self-Play (DFSP), which learns Nash equilibria through stochastic approximation. We evaluate the learned strategies in an emulation environment where real intrusions and response actions can be executed. The results show that the learned strategies approximate an equilibrium and that DFSP significantly outperforms a state-of-the-art algorithm for a realistic infrastructure configuration.

eess.SY↗