Papers for

industrial control teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Machine learning attacks target composed cyber physical systems

Data Manipulation Attacks Against Machine Learning Integrated Cyber-Physical Systems

Abstract: There is a well-established body of work demonstrating that individual machine learning (ML) algorithms can be manipulated or deceived. However, in many real-world systems, multiple ML algorithms are composed to enable automated decision-making, particularly in Cyber-Physical Systems (CPS). Often such systems use a composition of vision, planning, and other ML models to affect their internal state and ultimate take actions in the physical world. While there is a huge literature on the (in)security of ML algorithms, it is not immediately clear how an attacker might leverage their ability to trick individual learners when attacking the composition as a whole. We develop methods for creating an attack policy (a mapping from state to attack) for a data-manipulating attacker affecting a CPS or other state-machine-based AI compositions. We describe our framework, a basic threat model and corresponding methods for computing an optimal attack policy, as well as planned extensions. The goal of this work-in-progress paper is to stimulate conversation and forge new collaborations regarding the security of compositional learning.

Sun 8 NovMachine Learning
The gist
Machine learning models are often combined to control real-world devices like robots or smart infrastructure, but it’s unclear how attacks on single models affect the entire system. The authors study how an attacker could manipulate data to trick multiple connected machine learning components working together in these cyber-physical systems. They propose a way to create an attack plan that decides how to tamper with data based on the system’s state. This work aims to start discussions and collaborations about protecting such complex systems from coordinated attacks.
Open → 2611.11529v1

People understand shorter ai alerts faster in urgent tasks

Must AI Spell It Out? Pragmatic Comprehension of Alerts in a Time-Critical Task

Abstract: Assistive systems typically tell users everything, often spending time and attention on what a user already knows, leaving less for what happens next. People, on the other hand, leave out what they expect the listener can supply. Can people use their prior knowledge to understand an incomplete message when the speaker is a machine though? We studied this pragmatic comprehension in a monitoring task controlling users' prior knowledge and the available time to detect critical situations. In a preregistered study (N=114), we compared a pragmatic planner that reasons over a model of the listener's knowledge to decide what to say, when, and how explicitly, with a baseline specifying problems fully in onset order. Participants resolved underspecified alerts almost as reliably as fully specified ones and sooner, detected more problems, and rated the pragmatic assistant helpful more often, with no increase in reported mental demand. Our findings show that people can recover what the system left implicit and that pragmatic communication can support effective assistance under the constraints of a changing world.

Mon 2 NovHuman-Computer InteractionArtificial IntelligenceComputation and Language
The gist
Sometimes, AI assistants give very detailed warnings that repeat what users already know, which wastes time and attention. This paper shows that people can understand shorter, less detailed alerts if they already have some background knowledge. The authors ran a study where people controlled a monitoring task and found that these shorter alerts helped people spot problems faster and more often, without causing extra mental stress. This means AI can be more efficient by leaving out details users can fill in themselves.
Open → 2611.03976v1

Industrial system commands checked at execution time to avoid mistakes

Execution-Time Validation of Context-Carrying Action Intents in Industrial Cyber-Physical Systems

Abstract: In industrial cells, commands from learned policies, operators and schedulers reach the controller after inference, confirmation and transport, and the plant may have changed meanwhile, for instance by an operator pause. Such a command is released, or takes effect, when it is no longer correct. We call this the execution gap and ask which component should make the last check, and against which version of which state. The Action Intent Schema (AIS) is a contract in which a producer states how long its decision stays valid and what it assumes. The runtime XAIR rechecks each intent before release, can commit its authorization atomically in the context store, and can release it as a version-conditional command, which the controller executes only if its version of the state is unchanged. In controlled ablations with declared ground truth on emulated and physical cells, OpenPLC and ARM and RISC-V boards, a check on a replica always left an unprotected interval: a pause written from a few to over 100ms after submission escaped it. Only a check in the scan of a software controller, either a controller-local interlock or the version-conditional command, closed the interval for the state that controller owns; only the version-conditional command also refused commands after a pause that had been undone. A global version revoked up to every valid command under unrelated updates. Versions scoped to what the intent reads, or to the truth of its predicates, did not; with continuous signals on the variables the intent reads, only the latter avoided false revocations, though it burdens the store as predicates accumulate. On one embedded-board core, XAIR validated 148-168 intents/s.

Tue 20 OctProgramming LanguagesCryptography and SecurityDistributed, Parallel, and Cluster Computing
The gist
In factories, machines get instructions that might become outdated if something changes, like an operator pausing the process. The authors study how to make sure commands are still correct right before they happen, to avoid errors. They propose a system that double-checks these commands at the last moment and only lets the machine act if the situation is exactly as expected. Their tests show that some checks earlier in the process miss brief pauses, but checking at execution time closes this gap.
Open → 2610.27971v1

Evidence based selection improves agent pattern composition success

Selecting and Composing Agent Design Patterns: Industrial Case Evidence and Controlled Reference-System Experiments

Abstract: Agent pattern catalogs describe architectural alternatives, but engineers also need evidence for selecting and composing them. We extend a cognitive-function--execution-topology framework with an evidence-driven selection procedure and explicit composition contracts. The study combines two industrial case accounts, a contributor's collaboration design, seven practitioner workshops, and executable fault-injection experiments. Three local reference systems use SQLite state, shared artifact files, and a file-backed map-publication surrogate. A 2 x 2 ablation separates function-specific contracts from execution controls across 36 scenario families, with ten input variants per family. Under equal family weighting, composition correctly completes or safely refuses 11 of 12 families in each system, compared with 2, 2, and 1 for the simple baselines. These are constructed challenge-suite results, not production success rates. Recovery without consumer-side verification increases false-success cases in the map surrogate. All composed systems still fail a boundary case in which trusted evidence is wrong. An audit of a frozen six-arm language-model pilot reproduces its scores but confirms an evaluator-dependent ranking reversal. The contribution connects industrial failure, pattern selection, executable treatment, external acceptance, and revision. Selection is demonstrated rather than evaluated against an alternative procedure; catalog admission rests on separate criteria. The results support bounded composition mechanisms, not a claim that the framework improves engineers' design decisions over an equally informative conventional method.

Mon 19 OctSoftware EngineeringArtificial Intelligence
The gist
Choosing the right design patterns for software agents can be tricky because engineers need more than just options—they need evidence to know what works. The authors combine real-world cases with controlled experiments to test a new way of selecting and combining these patterns using contracts and measurable results. Their method succeeded much more often in completing tasks or safely refusing them than simpler baseline methods. However, some tricky cases still cause failures, especially when assumptions about trustworthy evidence fail. This study shows practical benefits of structured pattern use but does not claim to outperform all existing decision methods.
Open → 2610.25629v1

Remote monitor strategies minimize incorrect info age in pull systems

Minimizing Age of Incorrect Information in Pull-Based Remote Estimation of a Markov Source

Abstract: In this paper, we consider a discrete-time pull-based remote estimation system involving an information source and a remote monitor where the information source is a finite-state irreducible discrete-time Markov chain (DTMC) process. In this system, the remote monitor sends a pull request towards the source which responds by sampling its process so as to transmit the sampled values towards the monitor through a delay channel, encapsulated in information packets. We consider i) zero delay (ZD) and ii) unit delay (UD) channels, where the packet transmission times are zero and one slot, respectively. For remote estimation, we use the maximum a posteriori (MAP) estimator, and for quantifying its performance, we use the mean age of incorrect information (MAoII) which is a recently proposed freshness and mismatch metric that penalizes an incorrect estimation along with its duration. Our goal is to obtain pull policies so as to minimize MAoII under a long-run sampling rate constraint. For the ZD model, we propose a semi-Markov decision process (SMDP) formulation of the problem, which allows us to find the optimum observation-dependent pull policy. On the other hand, the UD channel prevents the monitor from possessing perfect information on the actual AoII process at any given time, and the SMDP formulation of the ZD channel cannot readily be used for the UD model. For the system with the UD channel, we first provide a numerical algorithm to calculate the MAoII and the average sampling rate for a given observation-dependent pull policy. For the optimization of the underlying remote estimation system, we use the joint distribution of the age and source processes to be obtained from the history of all observations, termed as belief. Subsequently, we propose a belief-dependent policy obtained via the belief-MDP formulation and a constrained deep reinforcement learning (CDRL) algorithm.

Thu 15 OctInformation TheoryNetworking and Internet Architecture
The gist
The paper looks at how a remote monitor can ask for updates from a changing information source to keep its data accurate. The authors focus on situations where updates take either no time or one time unit to arrive through a channel. They develop mathematical ways to decide the best times for the monitor to ask for updates, aiming to reduce how long and how often it holds wrong information. For the more complex one-unit delay case, they use advanced computation methods, including deep reinforcement learning, to find these best strategies.
Open → 2610.22265v1

Secure digital twins link actions observations and decisions clearly

SEAL-DT: An End-to-End Security Engineering and Assurance Framework for Cross-Domain Digital Twins

Abstract: Cyber-physical systems connect physical processes, software, networks and organizations. Securing them requires a clear account of what happened, what was observed, which actions were authorized and what evidence supports each decision. Digital Twin (DT) descriptions often fail to explain how these elements stay consistent, blur the distinction between physical events and uncertain observations, or detach simulation results from their requirements and assumptions. This paper presents SEAL-DT (Security Engineering and Assurance Lifecycle for Digital Twins), a structured approach to building and evaluating secure DTs. It brings entity definitions, process models, deterministic simulations, data contracts, evidence records, automated tests and reproducible results into one connected model. The main contribution is an end-to-end DT security framework, spanning scenario definition, entity/process modelling, simulation, security decision logic, evidence handling, validation and reproducible reporting. Security decisions and simulation results thus trace back to their data, assumptions and requirements. A DT is more than a copy of system state: it states what it can observe, how accurate and current its information is, where it came from and which decisions it may support. We demonstrate SEAL-DT in five scenarios: Car2X protection, passive IoT-device detection, an industrial control surrogate, lawful acquisition in a smart home, and medical-IoT monitoring that preserves continuity of care. Each includes formal models, deterministic and negative experiments, uncertainty analyses, schema-valid fixtures, technical reports and verified manifests, testing multiple configurations under normal and adverse conditions. Results show that the framework supports consistent model construction, traceable execution and comparable internal validation, and that security findings link to observable evidence.

Mon 12 OctCryptography and Security
The gist
Cyber-physical systems blend the physical world with software and networks, making security complicated because it's hard to track what really happened and why decisions were made. The authors created SEAL-DT, a complete framework to design and check digital twins that clearly show what they observe, how accurate that info is, and what supports each security decision. Their work helps keep simulation results honest and linked to real-world data and assumptions. They tested this framework in five different situations, showing that it helps build more trustworthy, understandable digital twins.
Open → 2610.17097v1

Hybrid deep learning improves malware detection with limited data

A Hybrid Approach to Malware Detection: Integrating Few-Shot Model-Agnostic Meta-Learning with Autoencoders

Abstract: Ransomware has emerged as a major cybersecurity threat, with incidents increasing in frequency and impact across critical sectors. These attacks are typically launched through phishing emails, malicious downloads, or exploitation of software vulnerabilities to gain system access. Once inside, the malware encrypts files and demands a ransom, often in cryptocurrency, for the decryption key. Conventional detection methods often struggle with novel or scarce samples, leaving systems vulnerable. To address these challenges, this paper proposes a hybrid deep learning framework that combines an Autoencoder Feature Extractor (AFE) with a Model Agnostic Meta Learning (MAML) classifier for few shot malware detection. The AFE generates compact latent features that reduce noise and dimensionality, while the MAML classifier rapidly adapts to new threats using limited labeled data. Experiments conducted on the Ransomware Dataset 2024 demonstrate the effectiveness of the framework in binary classification tasks. Across one to fifty shot settings, the proposed model consistently achieves high accuracy, F1 score, and Matthews Correlation Coefficient values, maintaining reliable classification even under extreme scarcity. These results highlight the model's robustness and effectiveness in adapting to limited data scenarios, demonstrating the potential of combining feature extraction with meta learning to enhance resilience against malware, particularly in sectors such as healthcare, manufacturing, and public infrastructure, where cyberattacks can cause significant operational and financial disruption.

Thu 1 OctCryptography and SecurityArtificial IntelligenceMachine Learning
The gist
Cyber attacks like ransomware lock up important files and demand payment to unlock them, causing big problems. Detecting new or rare malware is tough because there isn’t much data to learn from. The authors created a combined system that first simplifies the malware data to its key features, then uses a special learning method that can quickly adapt to new malware types even with few examples. Their tests show this method detects malware well even when only a small number of samples are available. This approach could help protect critical places like hospitals and factories from cyberattacks.
Open → 2610.01949v1

Building affordable one-way network devices using common hardware

Implementing Data Diodes Using Commodity Hardware and Open Source Software

Abstract: One-way network devices, known as data diodes, are used to defend against sophisticated cyberattacks. Partly due to their high cost, data diodes are mostly deployed in nuclear power plants and within the government for handling classified information. Although commercially available data diodes are expensive, a data diode's hardware can assembled from commodity fiber-optic network equipment. However, specialized software is needed to send data through a data diode reliably: the receiving program cannot request retransmission of dropped packets, so packet loss must be minimized and mitigated. First, we developed a minimal program to measure packet loss. We found that most packet loss was caused by the receiving program processing incoming packets too slowly, and that packet loss often occurs in clusters. Also, we discovered ways to minimize packet loss on Linux and macOS without using superuser privileges. Next, we tested three existing open source programs for one-way data transfers: netcat, UDPcast, and lidi. Although these programs were unreliable in their default configurations, we identified reliable configurations for UDPcast and lidi. Finally, we incorporated our findings into pydiode, our cross-platform program for reliable one-way data transfers.

Mon 28 SeptCryptography and SecurityNetworking and Internet Architecture
The gist
Data diodes are special devices that let information flow in only one direction to protect against cyberattacks. They are usually expensive and used in sensitive places like nuclear plants. The authors showed how to create reliable data diodes using regular, easy-to-get network parts and free software. They fixed problems with data loss and made a program called pydiode to send data safely without losing information. This makes one-way network security more affordable and accessible.
Open → 2609.35256v1

Modeling uncertainty and dependency improves multivariate time series anomaly detection

GT-PSSM: Unified Probabilistic Framework for Stochastic Dynamics Modeling and Dependency Learning in Multivariate Time Series Anomaly Detection

Abstract: Multivariate time series anomaly detection (MTAD) is crucial for ensuring the safe and reliable operation of complex systems. Many existing methods learn normal patterns by training reconstruction or forecasting models on predominantly normal data. However, a large portion of these approaches rely on deterministic models and their associated point-wise output errors for anomaly scoring. Since real-world multivariate time series are inherently stochastic due to measurement noise and intrinsic system randomness, purely error-based scores can be unreliable, as large errors may arise from benign fluctuations rather than true anomalies. Probabilistic approaches address this limitation by quantifying uncertainty in model outputs. In particular, probabilistic state-space models (PSSMs) provide a principled framework by modeling stochastic system dynamics through latent state transitions and measurement noise via emission models. Despite this advantage, existing PSSM-based MTAD methods often struggle to capture long-range temporal dependencies and inter-variable dependencies, as they typically rely on noise-sensitive recurrent architectures and lack explicit cross-variable structure modeling. To address these limitations, we propose Graph-Transformer-Enhanced Probabilistic State-Space Model (GT-PSSM), a novel PSSM-based MTAD method that tightly integrates PSSM-based probabilistic modeling of stochastic dynamics with Graph Transformer-based learning of temporal and inter-variable dependencies. By jointly modeling stochasticity, long-range temporal dependence, and variable interactions within a unified probabilistic framework, GT-PSSM enables more robust anomaly detection.

Mon 28 SeptMachine Learning
The gist
Finding unusual events in data that changes over time and across many parts is important for safety. The authors point out that usual methods often treat these data as predictable and may mistake normal random changes for problems. They created a new approach that combines a way to handle randomness with a method to understand both how things change over time and relate to each other. This combined approach helps detect true problems more reliably.
Open → 2609.34161v1