arXiv subjects

Ivan Petrov

Publications and source records attributed to Ivan Petrov.

9 recordsLinked to original sources

arXiv2026

Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages

LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks. By curating competitive programming problems, constantly adding fresh problems to the set, and filtering them by release dates, LCB provides contamination-aware evaluation and offers a holistic view of coding capability. However, LCB remains restricted to Python, leaving open the question of whether LLMs can generalize across the diverse programming languages required in real-world software engineering. We introduce Multi-LCB, a benchmark for evaluating LLMs across twelve programming languages, including Python. Multi-LCB transforms Python tasks from the LCB dataset into equivalent tasks in other languages while preserving LCB's contamination controls and evaluation protocol. Because it is fully compatible with the original LCB format, Multi-LCB will automatically track future LCB updates, enabling systematic assessment of cross-language code generation competence and requiring models to sustain performance well beyond Python. We evaluated 24 LLMs for instruction and reasoning on Multi-LCB, uncovering evidence of Python overfitting, language-specific contamination, and substantial disparities in multilingual performance. Our results establish Multi-LCB as a rigorous new benchmark for multi-programming-language code evaluation, directly addressing LCB's primary limitation and exposing critical gaps in current LLM capabilities.

cs.AI↗

arXiv2026

Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots

Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation backbones for honeypots. They enable defenders to construct high-interaction honeypots with low system security risks. However, LLM-powered honeypot development lacks a unified evaluation framework. Most evaluations consist of measuring response similarity on fixed commands, manual testing, or real-world deployment. These methods are often not scalable for development, reproducible across evaluations, representative of practical attacks, or adaptable to various attacker and honeypot configurations. In this work, we bridge this gap and propose Honeyval, a comprehensive evaluation framework for LLM-powered HTTP honeypots. We address the limitations of prior evaluations by grounding the honeypots in 16 backend applications, using AI hacking agents as attackers, employing two control tasks to monitor agent and honeypot capabilities across customizations, and defining clear and verifiable exploit goals for the attacker. Using Honeyval, we conduct an extensive evaluation of recent cost-efficient LLMs as HTTP honeypots. Our experiments highlight the promise of LLM-powered honeypots; they lead to substantially longer interactions with the attacker than rule-based baseline honeypots and are far less frequently detected even by frontier models, all while, on average, preserving a running cost advantage against agentic attackers. Further, we experiment with different counter-offensive honeypots configurations, and observe unique trade-offs, such as longer interactions at the cost of increased detection.

cs.CR↗

arXiv2025

Cardiac mortality prediction in patients undergoing PCI based on real and synthetic data

Patient status, angiographic and procedural characteristics encode crucial signals for predicting long-term outcomes after percutaneous coronary intervention (PCI). The aim of the study was to develop a predictive model for assessing the risk of cardiac death based on the real and synthetic data of patients undergoing PCI and to identify the factors that have the greatest impact on mortality. We analyzed 2,044 patients, who underwent a PCI for bifurcation lesions. The primary outcome was cardiac death at 3-year follow-up. Several machine learning models were applied to predict three-year mortality after PCI. To address class imbalance and improve the representation of the minority class, an additional 500 synthetic samples were generated and added to the training set. To evaluate the contribution of individual features to model performance, we applied permutation feature importance. An additional experiment was conducted to evaluate how the model's predictions would change after removing non-informative features from the training and test datasets. Without oversampling, all models achieve high overall accuracy (0.92-0.93), yet they almost completely ignore the minority class. Across models, augmentation consistently increases minority-class recall with minimal loss of AUROC, improves probability quality, and yields more clinically reasonable risk estimates on the constructed severe profiles. According to feature importance analysis, four features emerged as the most influential: Age, Ejection Fraction, Peripheral Artery Disease, and Cerebrovascular Disease. These results show that straightforward augmentation with realistic and extreme cases can expose, quantify, and reduce brittleness in imbalanced clinical prediction using only tabular records, and motivate routine reporting of probability quality and stress tests alongside headline metrics.

cs.LG↗

arXiv2025

Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world impact of such prediction-altering attacks has remained unclear. In this paper we introduce a novel and significantly more potent class of backdoors that builds upon recent advancements in architectural backdoors. We demonstrate how these backdoors can be specifically engineered to exploit batched inference, a common technique for hardware utilization, enabling large-scale user data manipulation and theft. By targeting the batching process, these architectural backdoors facilitate information leakage between concurrent user requests and allow attackers to fully control model responses directed at other users within the same batch. In other words, an attacker who can change the model architecture can set and steal model inputs and outputs of other users within the same batch. We show that such attacks are not only feasible but also alarmingly effective, can be readily injected into prevalent model architectures, (e.g. Transformers), and represent a truly malicious threat to user privacy and system integrity. Critically, to counteract this new class of vulnerabilities, we propose a deterministic mitigation strategy that provides formal guarantees against this new attack vector, unlike prior work that relied on LLMs to find the backdoors. Our mitigation strategy employs a novel Information Flow Control mechanism that analyzes the model graph and proves non-interference between different user inputs within the same batch. Using our mitigation strategy we perform a large scale analysis of models hosted through Hugging Face and find over 200 models that introduce (unintended) information leakage between batch entries due to the use of dynamic quantization.

cs.CR↗

arXiv2024

A Confidential Computing Transparency Framework for a Comprehensive Trust Chain

Confidential Computing enhances privacy of data in-use through hardware-based Trusted Execution Environments (TEEs) that use attestation to verify their integrity, authenticity, and certain runtime properties, along with those of the binaries they execute. However, TEEs require user trust, as attestation alone cannot guarantee the absence of vulnerabilities or backdoors. Enhanced transparency can mitigate the reliance on naive trust. Some organisations currently employ various transparency measures, including open-source firmware, publishing technical documentation, or undergoing external audits, but these require investments with unclear returns. This may discourage the adoption of transparency, leaving users with limited visibility into system privacy measures. Additionally, the lack of standardisation complicates meaningful comparisons between implementations. To address these challenges, we propose a three-level conceptual framework providing organisations with a practical pathway to incrementally improve Confidential Computing transparency. To evaluate whether our transparency framework contributes to an increase in end-user trust, we conducted an empirical study with over 800 non-expert participants. The results indicate that greater transparency improves user comfort, with participants willing to share various types of personal data across different levels of transparency. The study also reveals misconceptions about transparency, highlighting the need for clear communication and user education.

cs.CR↗

arXiv2023

Asymmetric adaptive LDPC-based information reconciliation for industrial quantum key distribution

We develop a new approach for asymmetric LDPC-based information reconciliation in order to adapt to the current channel state and achieve better performance and scalability in practical resource-constrained QKD systems. The new scheme combines the advantages of LDPC codes, a priori error rate estimation, rate-adaptive and blind information reconciliation techniques. We compare the performance of several asymmetric and symmetric error correction schemes using real industrial QKD setup. The proposed asymmetric algorithm achieves significantly higher throughput, providing a secret key rate very close to the symmetric one in a wide range of error rates. Thus, our approach turns out to be particularly efficient for applications with high key rates, limited classical channel capacity and asymmetric computational resource allocation.

quant-ph↗

arXiv2021

Scalable synthesis of 2D van der Waals superlattices

Heterostructure materials form the basis of much of modern electronics, from transistors to lasers and light-emitting diodes. Recent years have seen a renewed focus on creating heterostructures through the vertical integration of two-dimensional materials, including graphene, hexagonal boron nitride, and transition metal dichalcogenides (TMDCs). However, fundamental challenges associated with materials processing have limited material quality and impeded scalability. We demonstrate a method to convert sub-nanometer metal films deposited on silicon and sapphire into TMDC heterostructures through vapor-phase processing. The resulting heterostructures and superlattices exhibit novel properties compared with stand-alone TMDCs, including reduced bandgap, enhanced light-matter coupling, and improved catalytic performance. This robust and scalable synthetic method provides new opportunities to generate a wide range of artificially stacked 2D superlattices with controlled morphology and composition.

cond-mat.mtrl-sci↗

arXiv2020

CoinPolice:Detecting Hidden Cryptojacking Attacks with Neural Networks

Traffic monetization is a crucial component of running most for-profit online businesses. One of its latest incarnations is cryptocurrency mining, where a website instructs the visitor's browser to participate in building a cryptocurrency ledger (e.g., Bitcoin, Monero) in exchange for a small reward in the same currency. In its essence, this practice trades the user's electric bill (or battery level) for cryptocurrency. With user consent, this exchange can be a legitimate funding source - for example, UNICEF has collected over 27k charity donations on a website dedicated to this purpose, thehopepage.org. Regrettably, this practice also easily lends itself to abuse: in this form, called cryptojacking, attacks surreptitiously mine in the users browser, and profits are collected either by website owners or by hackers that planted the mining script into a vulnerable page. Cryptojackers have been bettering their evasion techniques, incorporating in their toolkits domain fluxing, content obfuscation, the use of WebAssembly, and throttling. Whereas most state-of-the-art defenses address multiple of these evasion techniques, none is resistant against all. In this paper, we offer a novel detection method, CoinPolice, that is robust against all of the aforementioned evasion techniques. CoinPolice flips throttling against cryptojackers, artificially varying the browser's CPU power to observe the presence of throttling. Based on a deep neural network classifier, CoinPolice can detect 97.87% of hidden miners with a low false positive rate (0.74%). We compare CoinPolice performance with the current state of the art and show our approach outperforms it when detecting aggressively throttled miners. Finally, we deploy Coinpolice to perform the largest-scale cryptoming investigation to date, identifying 6700 sites that monetize traffic in this fashion.

cs.CR↗

arXiv2019

Mechanical properties of VMoNO as a function of oxygen concentration: toward development of hard and tough refractory oxynitrides

Improved toughness is a central goal in the development of wear-resistant refractory ceramic coatings. Extensive theoretical and experimental research has revealed that NaCl structure VMoN alloys exhibit surprisingly high ductility combined with high hardness and toughness. However, during operation, protective coatings inevitably oxidize, a problem which may compromise material properties and performance. Here, we explore the role of oxidation in altering VMoN properties. Density functional theory and theoretical intrinsic hardness models are used to investigate the mechanical behavior of cubic V0.5Mo0.5N1-xOx solid solutions as a function of the oxygen concentration x. Elastic-constant and intrinsic hardness calculations show that oxidation does not degrade the mechanical properties of V0.5Mo0.5N. Electronic structure analyses indicate that the presence of oxygen reduces the covalent bond character, which slightly lowers the alloy strength and intrinsic hardness. Nevertheless, the character of metallic d-d states, which are crucial for allowing plastic deformation and enhancing toughness, remains unaffected. Overall, our results suggest that VMoNO oxynitrides, with oxygen concentrations as high as 50%, possess high intrinsic hardness, while still being ductile.

cond-mat.mtrl-sci↗