arXiv subjects

Tansu Alpcan

Publications and source records attributed to Tansu Alpcan.

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

When cheap gradients fail: the measurement cost of attacking quantum classifiers

Adversarial perturbations threaten machine learning classifiers, including variational quantum classifiers. We show that finite quantum measurement statistics (shot noise) act as a built-in defense against gradient-based test-time attacks whose cost scales unfavorably for the attacker. Because every gradient component must be inferred from repeated circuit executions under any unbiased gradient-estimation rule, white-box extraction consumes a dimension-dependent measurement budget that measurement grouping cannot remove in expressive circuits. Under stated assumptions, single-step attacks need at least quadratically many shots in the input dimension $d$, growing as $d^{5/2}$ under norm-concentration scaling, with a sufficient-budget analysis for iterative attacks via stochastic gradient Langevin dynamics. Simulations up to 784 input dimensions validate the law: the realized total budget is the $d^{5/2}$ geometric floor for plateau-mitigated models and grows as $d^{3.00}$ for the tested deep circuits, whose gradient norms decay with dimension absent barren-plateau mitigation; folding the measured gradient norm back in recovers the parameter-free $d^{3/2}$ shot-noise geometry. Against a matched classical baseline whose attack overhead is dimension-independent (the cheap-gradient principle of automatic differentiation), the quantum gradient cost ratio grows empirically as $d^{3.00}$, so the attacker's relative cost diverges as the model scales. Experiments on a 156-qubit IBM processor (ibm_boston, 4-qubit circuits, $d=12$) reproduce the effect: at matched budgets the device attack tracks the ideal within a few percent, with the high-shot gradient faithful to the exact one. The defense operates precisely when the forward map is classically hard to simulate: only then is a white-box attacker denied the simulate-and-backpropagate shortcut and must pay the measurement cost we quantify.

quant-ph↗

arXiv2026

Fortifying Time Series: DTW-Certified Robust Anomaly Detection

Time-series anomaly detection is critical for ensuring safety in high-stakes applications, where robustness is a fundamental requirement rather than a mere performance metric. Addressing the vulnerability of these systems to adversarial manipulation is therefore essential. Existing defenses are largely heuristic or provide certified robustness only under $\ell_p$-norm constraints, which are incompatible with time-series data. In particular, $\ell_p$-norm fails to capture the intrinsic temporal structure in time series, causing small temporal distortions to significantly alter the $\ell_p$-norm measures. Instead, the similarity metric \emph{Dynamic Time Warping} (DTW) is more suitable and widely adopted in the time-series domain, as DTW accounts for temporal alignment and remains robust to temporal variations. To date, however, there has been no certifiable robustness result in this metric that provides guarantees. In this work, we introduce the first \emph{DTW-certified robust defense} in time-series anomaly detection by adapting the randomized smoothing paradigm. We develop this certificate by bridging the $\ell_p$-norm to DTW distance through a lower-bound transformation. Extensive experiments across various datasets and models validate the effectiveness and practicality of our theoretical approach. Results demonstrate significantly improved performance, e.g., up to 18.7\% in F1-score under DTW-based adversarial attacks compared to traditional certified models.

cs.LG↗

arXiv2026

Parameter-efficient Quantum Multi-task Learning

Multi-task learning (MTL) improves generalization and data efficiency by jointly learning related tasks through shared representations. In the widely used hard-parameter-sharing setting, a shared backbone is combined with task-specific prediction heads. However, task-specific parameters can grow rapidly with the number of tasks. Therefore, designing multi-task heads that preserve task specialization while improving parameter efficiency remains a key challenge. In Quantum Machine Learning (QML), variational quantum circuits (VQCs) provide a compact mechanism for mapping classical data to quantum states residing in high-dimensional Hilbert spaces, enabling expressive representations within constrained parameter budgets. We propose a parameter-efficient quantum multi-task learning (QMTL) framework that replaces conventional task-specific linear heads with a fully quantum prediction head in a hybrid architecture. The model consists of a VQC with a shared, task-independent quantum encoding stage, followed by lightweight task-specific ansatz blocks enabling localized task adaptation while maintaining compact parameterization. Under a controlled and capacity-matched formulation where the shared representation dimension grows with the number of tasks, our parameter-scaling analysis demonstrates that a standard classical head exhibits quadratic growth, whereas the proposed quantum head parameter cost scales linearly. We evaluate QMTL on three multi-task benchmarks spanning natural language processing, medical imaging, and multimodal sarcasm detection, where we achieve performance comparable to, and in some cases exceeding, classical hard-parameter-sharing baselines while consistently outperforming existing hybrid quantum MTL models with substantially fewer head parameters. We further demonstrate QMTL's executability on noisy simulators and real quantum hardware, illustrating its feasibility.

cs.LG↗

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

Intention-aware Hierarchical Diffusion Model for Long-term Trajectory Anomaly Detection

Long-term trajectory anomaly detection is a challenging problem due to the diversity and complex spatiotemporal dependencies in trajectory data. Existing trajectory anomaly detection methods fail to simultaneously consider both the high-level intentions of agents as well as the low-level details of the agent's navigation when analysing an agent's trajectories. This limits their ability to capture the full diversity of normal trajectories. In this paper, we propose an unsupervised trajectory anomaly detection method named Intention-aware Hierarchical Diffusion model (IHiD), which detects anomalies through both high-level intent evaluation and low-level sub-trajectory analysis. Our approach leverages Inverse Q Learning as the high-level model to assess whether a selected subgoal aligns with an agent's intention based on predicted Q-values. Meanwhile, a diffusion model serves as the low-level model to generate sub-trajectories conditioned on subgoal information, with anomaly detection based on reconstruction error. By integrating both models, IHiD effectively utilises subgoal transition knowledge and is designed to capture the diverse distribution of normal trajectories. Our experiments show that the proposed method IHiD achieves up to 30.2% improvement in anomaly detection performance in terms of F1 score over state-of-the-art baselines.

cs.AI↗

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

A Qubit-Efficient Hybrid Quantum Encoding Mechanism for Quantum Machine Learning

Efficiently embedding high-dimensional datasets onto noisy and low-qubit quantum systems is a significant barrier to practical Quantum Machine Learning (QML). Approaches such as quantum autoencoders can be constrained by current hardware capabilities and may exhibit vulnerabilities to reconstruction attacks due to their invertibility. We propose Quantum Principal Geodesic Analysis (qPGA), a novel, non-invertible method for dimensionality reduction and qubit-efficient encoding. Executed classically, qPGA leverages Riemannian geometry to project data onto the unit Hilbert sphere, generating outputs inherently suitable for quantum amplitude encoding. This technique preserves the neighborhood structure of high-dimensional datasets within a compact latent space, significantly reducing qubit requirements for amplitude encoding. We derive theoretical bounds quantifying qubit requirements for effective encoding onto noisy systems. Empirical results on MNIST, Fashion-MNIST, and CIFAR-10 show that qPGA preserves local structure more effectively than both quantum and hybrid autoencoders. Additionally, we demonstrate that qPGA enhances resistance to reconstruction attacks due to its non-invertible nature. In downstream QML classification tasks, qPGA can achieve over 99% accuracy and F1-score on MNIST and Fashion-MNIST, outperforming quantum-dependent baselines. Initial tests on real hardware and noisy simulators confirm its potential for noise-resilient performance, offering a scalable solution for advancing QML applications.

quant-ph↗

arXiv2024

Computable Model-Independent Bounds for Adversarial Quantum Machine Learning

By leveraging the principles of quantum mechanics, QML opens doors to novel approaches in machine learning and offers potential speedup. However, machine learning models are well-documented to be vulnerable to malicious manipulations, and this susceptibility extends to the models of QML. This situation necessitates a thorough understanding of QML's resilience against adversarial attacks, particularly in an era where quantum computing capabilities are expanding. In this regard, this paper examines model-independent bounds on adversarial performance for QML. To the best of our knowledge, we introduce the first computation of an approximate lower bound for adversarial error when evaluating model resilience against sophisticated quantum-based adversarial attacks. Experimental results are compared to the computed bound, demonstrating the potential of QML models to achieve high robustness. In the best case, the experimental error is only 10% above the estimated bound, offering evidence of the inherent robustness of quantum models. This work not only advances our theoretical understanding of quantum model resilience but also provides a precise reference bound for the future development of robust QML algorithms.

cs.LG↗

arXiv2024

A Hybrid Quantum Neural Network for Split Learning

Quantum Machine Learning (QML) is an emerging field of research with potential applications to distributed collaborative learning, such as Split Learning (SL). SL allows resource-constrained clients to collaboratively train ML models with a server, reduce their computational overhead, and enable data privacy by avoiding raw data sharing. Although QML with SL has been studied, the problem remains open in resource-constrained environments where clients lack quantum computing capabilities. Additionally, data privacy leakage between client and server in SL poses risks of reconstruction attacks on the server side. To address these issues, we propose Hybrid Quantum Split Learning (HQSL), an application of Hybrid QML in SL. HQSL enables classical clients to train models with a hybrid quantum server and curtails reconstruction attacks. Additionally, we introduce a novel qubit-efficient data-loading technique for designing a quantum layer in HQSL, minimizing both the number of qubits and circuit depth. Evaluations on real hardware demonstrate HQSL's practicality under realistic quantum noise. Experiments on five datasets demonstrate HQSL's feasibility and ability to enhance classification performance compared to its classical models. Notably, HQSL achieves mean improvements of over 3% in both accuracy and F1-score for the Fashion-MNIST dataset, and over 1.5% in both metrics for the Speech Commands dataset. We expand these studies to include up to 100 clients, confirming HQSL's scalability. Moreover, we introduce a noise-based defense mechanism to tackle reconstruction attacks on the server side. Overall, HQSL enables classical clients to train collaboratively with a hybrid quantum server, improving model performance and resistance against reconstruction attacks.

quant-ph↗

arXiv2024

An Efficient Wireless Channel Estimation Model for Environment Sensing

This paper presents a novel and efficient wireless channel estimation scheme based on a tapped delay line (TDL) model of wireless signal propagation, where a data-driven machine learning approach is used to estimate the path delays and gains. The key motivation for our novel channel estimation model is to gain environment awareness, i.e., detecting changes in path delays and gains related to interesting objects and events in the field. The estimated channel state provides a more detailed measure to sense the field than the single-tap channel state indicator (CSI) in current OFDM systems. Advantages of this approach also include low computation time and training data requirements, making it suitable for environment awareness applications. We evaluate this model's performance using Matlab's ray-tracing tool under static and dynamic conditions for increased realism instead of the standard evaluation approaches that rely on classical statistical channel models. Our results show that our TDL-based model can accurately estimate the path delays and associated gains for a broad-range of locations and operating conditions. Root-mean-square estimation error was less than $10^{-4}$, or $-40$dB, for SNR $\geq 60$dB in all of our experiments. Our results show that interference of a flying drone on signal multipaths, in a preliminary experiment, can be detected in estimated channel states which, otherwise, remains obscured in conventional CSI.

cs.NI↗

arXiv2024

Lightweight Conceptual Dictionary Learning for Text Classification Using Information Compression

We propose a novel, lightweight supervised dictionary learning framework for text classification based on data compression and representation. This two-phase algorithm initially employs the Lempel-Ziv-Welch (LZW) algorithm to construct a dictionary from text datasets, focusing on the conceptual significance of dictionary elements. Subsequently, dictionaries are refined considering label data, optimizing dictionary atoms to enhance discriminative power based on mutual information and class distribution. This process generates discriminative numerical representations, facilitating the training of simple classifiers such as SVMs and neural networks. We evaluate our algorithm's information-theoretic performance using information bottleneck principles and introduce the information plane area rank (IPAR) as a novel metric to quantify the information-theoretic performance. Tested on six benchmark text datasets, our algorithm competes closely with top models, especially in limited-vocabulary contexts, using significantly fewer parameters. \review{Our algorithm closely matches top-performing models, deviating by only ~2\% on limited-vocabulary datasets, using just 10\% of their parameters. However, it falls short on diverse-vocabulary datasets, likely due to the LZW algorithm's constraints with low-repetition data. This contrast highlights its efficiency and limitations across different dataset types.

cs.CL↗

arXiv2024

OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences

Anomaly detection in decision-making sequences is a challenging problem due to the complexity of normality representation learning and the sequential nature of the task. Most existing methods based on Reinforcement Learning (RL) are difficult to implement in the real world due to unrealistic assumptions, such as having access to environment dynamics, reward signals, and online interactions with the environment. To address these limitations, we propose an unsupervised method named Offline Imitation Learning based Anomaly Detection (OIL-AD), which detects anomalies in decision-making sequences using two extracted behaviour features: action optimality and sequential association. Our offline learning model is an adaptation of behavioural cloning with a transformer policy network, where we modify the training process to learn a Q function and a state value function from normal trajectories. We propose that the Q function and the state value function can provide sufficient information about agents' behavioural data, from which we derive two features for anomaly detection. The intuition behind our method is that the action optimality feature derived from the Q function can differentiate the optimal action from others at each local state, and the sequential association feature derived from the state value function has the potential to maintain the temporal correlations between decisions (state-action pairs). Our experiments show that OIL-AD can achieve outstanding online anomaly detection performance with up to 34.8% improvement in F1 score over comparable baselines.

cs.LG↗

arXiv2023

Game-Theoretic Analysis of Adversarial Decision Making in a Complex Sociophysical System

We apply Game Theory to a mathematical representation of two competing teams of agents connected within a complex network, where the ability of each side to manoeuvre their resource and degrade that of the other depends on their ability to internally synchronise decision-making while out-pacing the other. Such a representation of an adversarial socio-physical system has application in a range of business, sporting, and military contexts. Specifically, we unite here two physics-based models, that of Kuramoto to represent decision-making cycles, and an adaptation of a multi-species Lotka-Volterra system for the resource competition. For complex networks we employ variations of the Barabási-Alberts scale-free graph, varying how resources are initially distributed between graph hub and periphery. We adapt as equilibrium solution Nash Dominant Game Pruning as a means of efficiently exploring the dynamical decision tree. Across various scenarios we find Nash solutions where the side initially concentrating resources in the periphery can sustain competition to achieve victory except when asymmetries exist between the two. When structural advantage is limited we find that agility in how the victor stays ahead of decision-state of the other becomes critical.

physics.soc-ph↗

arXiv2023

Artificial Intelligence Techniques for Next-Generation Mega Satellite Networks

Space communications, particularly massive satellite networks, re-emerged as an appealing candidate for next generation networks due to major advances in space launching, electronics, processing power, and miniaturization. However, massive satellite networks rely on numerous underlying and intertwined processes that cannot be truly captured using conventionally used models, due to their dynamic and unique features such as orbital speed, inter-satellite links, short pass time, and satellite footprint, among others. Hence, new approaches are needed to enable the network to proactively adjust to the rapidly varying conditions associated within the link. Artificial intelligence (AI) provides a pathway to capture these processes, analyze their behavior, and model their effect on the network. This article introduces the application of AI techniques for integrated terrestrial satellite networks, particularly massive satellite network communications. It details the unique features of massive satellite networks, and the overarching challenges concomitant with their integration into the current communication infrastructure. Moreover, this article provides insights into state-of-the-art AI techniques across various layers of the communication link. This entails applying AI for forecasting the highly dynamic radio channel, spectrum sensing and classification, signal detection and demodulation, inter-satellite and satellite access network optimization, and network security. Moreover, future paradigms and the mapping of these mechanisms onto practical networks are outlined.

cs.NI↗

arXiv2023

Failure-tolerant Distributed Learning for Anomaly Detection in Wireless Networks

The analysis of distributed techniques is often focused upon their efficiency, without considering their robustness (or lack thereof). Such a consideration is particularly important when devices or central servers can fail, which can potentially cripple distributed systems. When such failures arise in wireless communications networks, important services that they use/provide (like anomaly detection) can be left inoperable and can result in a cascade of security problems. In this paper, we present a novel method to address these risks by combining both flat- and star-topologies, combining the performance and reliability benefits of both. We refer to this method as "Tol-FL", due to its increased failure-tolerance as compared to the technique of Federated Learning. Our approach both limits device failure risks while outperforming prior methods by up to 8% in terms of anomaly detection AUROC in a range of realistic settings that consider client as well as server failure, all while reducing communication costs. This performance demonstrates that Tol-FL is a highly suitable method for distributed model training for anomaly detection, especially in the domain of wireless networks.

cs.LG↗