Ivo Gergov

Mr. Ivo Gergov

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 September 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
IGIvo Gergov
Ivo Gergov
Georgi TsochevGeorgi Tsochev
Georgi Tsochev
Large Language Models are often fine-tuned on proprietary corpora, motivating reliable provenance signals. A corpus-level watermark method is proposed for fine-tuning datasets that survives training and common text transformations. The method subtly biases synonym choices according to a secret key (PRF) and encodes a multi-bit payload with an error-correcting code, enabling keyed detection via a generalized likelihood ratio test with permutation-calibrated p-values. For short offline passages (~100 words), the channel is valid but statistically underpowered: the average density is ~0.0165, and the median p-value is close to 1.0. In generative tests with Mistral 7B across 12 configurations and 12,720 texts, 0.00% detection was observed at very high quality (~99.8%). As limited base cases, positive detection was reported for other setups: 8.9% (offline), 5.0% (Mistral 7B), and 3.0% (Llama2-13B). A permutation test (R = 5000), confidence intervals, and power analysis were added. Quality impact statements were refined, with “minimal impact” used instead of “imperceptible.” In this study, limitations and ethical use are discussed, and directions for stronger semantic channels and model-based detectors are outlined.

25 May 2026 in Sustainability
Verified
Journal Article
Open access
PDF file
IGIvo Gergov
Ivo Gergov
MSMaksim Sharabov
Maksim Sharabov
ARAlexander Rusev
Alexander Rusev
Georgi TsochevGeorgi Tsochev
Georgi Tsochev
Critical infrastructure restoration (CIR) is a disaster-management and sustainability challenge because prolonged disruption of energy, water, transport, communications, healthcare, and public-administration services can amplify social, economic, and environmental losses. This PRISMA 2020-reported systematic review synthesizes post-2016 scientific literature and official policy, legal, standards, and technical documents on CIR and AI decision support. The review identified 55 records, removed 1 duplicate, excluded 1 ineligible record, and retained 53 core sources for qualitative synthesis, including 31 scholarly publications and 22 official documents. Manual screening was used; no automated screening or AI-assisted exclusion tools were applied. The results are organized around four research questions covering regulatory frameworks, recovery practices, supporting systems, and AI model families. The synthesis shows that CIR is shaped by layered governance through NIS2, the CER Directive, the AI Act, and national measures; by operational recovery practices such as continuity planning, cyber crisis coordination, interdependency mapping, and model-supported restoration; by digital platforms including SCADA/ICS, IoT sensing, GIS/common operating pictures, decision-support systems, simulation environments, and digital twins; and by AI methods ranging from classical machine learning and computer vision to reinforcement learning and generative assistants. However, evidence maturity remains uneven, with many AI applications still simulation-based, sector-specific, or weakly validated in real restoration settings. The review contributes an integrated CIR-oriented framework showing that AI creates practical value when embedded in interoperable, human-supervised, regulation-aware, and empirically validated restoration architectures that support sustainable service continuity rather than isolated automation.

1 June 2026 in Future Internet
Verified
Journal Article
Open access
PDF file
Georgi TsochevGeorgi Tsochev
Georgi Tsochev
IGIvo Gergov
Ivo Gergov
Critical infrastructures are increasingly Internet-connected cyber–physical systems whose recovery after cyber incidents must satisfy safety, timing, regulatory, and interdependency constraints. Yet, the use of large language models (LLMs) for generating recovery plans remains fragmented across cybersecurity, industrial control, digital twins, and AI assurance research. This review synthesizes that emerging field through a structured critical survey of studies on LLMs in incident response, OT/ICS resilience, and cyber–physical recovery, with a focused perspective on grounding, trust, and assurance mechanisms relevant to recovery-plan generation. It develops an architecture-centric taxonomy spanning prompt-only assistants, retrieval-augmented copilots, graph-aware planners, multi-agent systems, and hybrid verification/simulation pipelines; maps realistic applications across energy, water, manufacturing, transportation, healthcare, and telecommunications; and organizes limitations into technical, security, governance, and human-factor categories. Based on this synthesis, the paper proposes the Grounded Recovery Planning Stack as a reference architecture and outlines a staged roadmap from human-in-the-loop copilots to bounded orchestration. The main conclusion is that near-term value lies in grounded, auditable, compliance-aware copilots, whereas autonomous recovery execution remains premature without stronger validation, state-aware grounding, sector-specific benchmarks, and formal safeguards.

25 May 2026 in Mathematics
Verified
Journal Article
Open access
PDF file
IGIvo Gergov
Ivo Gergov
Georgi TsochevGeorgi Tsochev
Georgi Tsochev
AAAdelina Aleksieva-Petrova
Adelina Aleksieva-Petrova
Decentralized compute markets require autonomous agents to negotiate heterogeneous resources under budget constraints, stochastic supply, and strategic interaction. We present Agora-RL, a reproducibility-first benchmark for repeated negotiation of GPU, memory, and bandwidth through token-denominated double auctions. The study asks two questions: how standard MARL baselines rank when reward, social welfare, and inequality are evaluated jointly; and whether a transparent benchmark protocol can make such comparisons auditable. PPO, MAPPO, MADDPG, and IQL are evaluated with matched 300-episode training budgets, 30 deterministic evaluation episodes, and 12 random seeds. Using percentile-bootstrap 95% confidence intervals, MAPPO achieves the highest reward (0.0140 [0.0124, 0.0154]) and social welfare (0.0952 [0.0854, 0.1045]), whereas IQL yields the lowest Gini coefficient (0.4477 [0.4360, 0.4613]). Secondary diagnostics show that reward leadership does not imply fairness, equilibrium closeness, or communication robustness. The contribution is an empirical benchmark and audit protocol rather than a new auction theorem or blockchain settlement layer.