Alexandros Karakikes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Alexandros Karakikes has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Konstantinos Kotis
Intelligent Systems Lab, Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece
3 shared publications - Andreas Soularidis
Intelligent Systems Laboratory, Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece
2 shared publications - Dimitrios Doumanas
Intelligent Systems Laboratory, Department of Cultural Technology and Communication, University of the Aegean, 81100 Mytilene, Greece
2 shared publications - Efstathios Mainas
Fusion Unit, European Integrated Border Management (EIBM), Intelligence Division, Frontex, Plac Europejski 6, 00-844 Warsaw, Poland
2 shared publications
Latest Publications
- Open Access
- 10 December 2025
- Published by MDPI AG in Information
- Vol. 16 (12) , 1095
AI-Assisted OSINT/SOCMINT for Safeguarding Borders: A Systematic Review
In the highly volatile realm of global security, the necessity for leading-edge and effectual border resilience tactics has never been more imperative. This PRISMA 2020 guided systematic literature review (SLR) examines the intersection of artificial intelligence (AI), open-source intelligence (OSINT), and social media intelligence (SOCMINT) for enhancing border protection. Our systematic investigation across major databases (IEEE Xplore, Scopus, SpringerLink, MDPI, ACM) and grey literature sources yielded 3932 initial records and, after screening and eligibility assessment, 73 studies and reports from acknowledged organizations, contributing to the evidence synthesis. Three research questions (RQ1–RQ3) were addressed concerning the following: (a) the effectiveness and application of AI in OSINT/SOCMINT for border protection, its (b) data, technical, and operational limitations, and its (c) ethical, legal, and societal implications (GELSI). Evidence matrices summarize the findings, while narrative syntheses underline and thematically group the extracted insights. Results indicate that AI techniques—fluctuating from machine learning (ML) and natural language processing (NLP) to computer vision and emerging large language models (LLMs)—produce quantifiable improvements in forecasting irregular migration, detecting human trafficking, and supporting multimodal intelligence fusion. However, limitations include misinformation, data bias, adversarial vulnerabilities, governance deficits, and sandbox-to-production gaps. Ethical and societal concerns highlight risks of surveillance overreach, discrimination, and insufficient oversight, among others. To our knowledge, this is the first SLR at this intersection. We conclude that, AI-assisted OSINT/SOCMINT presents transformative potential for border protection requiring, nonetheless, balanced governance, robust validation, and future research on LLM/agentic AI, human–AI teaming, and oversight mechanisms.
- 10 December 2025
- Published by MDPI AG in Information
- Vol. 16 (12) , 1095
Open AccessAI-Assisted OSINT/SOCMINT for Safeguarding Borders: A Systematic Review
In the highly volatile realm of global security, the necessity for leading-edge and effectual border resilience tactics has never been more imperative. This PRISMA 2020 guided systematic literature review (SLR) examines the intersection of artificial intelligence (AI), open-source intelligence (OSINT), and social media intelligence (SOCMINT) for enhancing border protection. Our systematic investigation across major databases (IEEE Xplore, Scopus, SpringerLink, MDPI, ACM) and grey literature sources yielded 3932 initial records and, after screening and eligibility assessment, 73 studies and reports from acknowledged organizations, contributing to the evidence synthesis. Three research questions (RQ1–RQ3) were addressed concerning the following: (a) the effectiveness and application of AI in OSINT/SOCMINT for border protection, its (b) data, technical, and operational limitations, and its (c) ethical, legal, and societal implications (GELSI). Evidence matrices summarize the findings, while narrative syntheses underline and thematically group the extracted insights. Results indicate that AI techniques—fluctuating from machine learning (ML) and natural language processing (NLP) to computer vision and emerging large language models (LLMs)—produce quantifiable improvements in forecasting irregular migration, detecting human trafficking, and supporting multimodal intelligence fusion. However, limitations include misinformation, data bias, adversarial vulnerabilities, governance deficits, and sandbox-to-production gaps. Ethical and societal concerns highlight risks of surveillance overreach, discrimination, and insufficient oversight, among others. To our knowledge, this is the first SLR at this intersection. We conclude that, AI-assisted OSINT/SOCMINT presents transformative potential for border protection requiring, nonetheless, balanced governance, robust validation, and future research on LLM/agentic AI, human–AI teaming, and oversight mechanisms.
- Open Access
Emerging Threat Vectors: How Malicious Actors Exploit LLMs to Undermine Border Security
The rapid proliferation of Large Language Models (LLMs) has democratized access to advanced generative capabilities while raising urgent concerns about misuse in sensitive security domains. Border security, in particular, represents a high-risk environment where malicious actors may exploit LLMs for document forgery, synthetic identity creation, logistics planning, or disinformation campaigns. Existing studies often highlight such risks in theory, yet few provide systematic empirical evidence of how state-of-the-art LLMs can be exploited. This paper introduces the Silent Adversary Framework (SAF), a structured pipeline that models the sequential stages by which obfuscated prompts can covertly bypass safeguards. We evaluate ten high-risk scenarios using five leading models—GPT-4o, Claude 3.7 Sonnet, Gemini 2.5 Flash, Grok 3, and Runway Gen-2—and assess outputs through three standardized metrics: Bypass Success Rate (BSR), Output Realism Score (ORS), and Operational Risk Level (ORL). Results reveal that, while all models exhibited some susceptibility, vulnerabilities were heterogeneous. Claude showed greater resistance in chemistry-related prompts, whereas GPT-4o and Gemini generated highly realistic outputs in identity fraud and logistics optimization tasks. Document forgery attempts produced only partially successful templates that lacked critical security features. These findings highlight the uneven distribution of risks across models and domains. By combining a reproducible adversarial framework with empirical testing, this study advances the evidence base on LLM misuse and provides actionable insights for policymakers and border security agencies, underscoring the need for stronger safeguards and oversight in the deployment of generative AI.
Open AccessEmerging Threat Vectors: How Malicious Actors Exploit LLMs to Undermine Border Security
The rapid proliferation of Large Language Models (LLMs) has democratized access to advanced generative capabilities while raising urgent concerns about misuse in sensitive security domains. Border security, in particular, represents a high-risk environment where malicious actors may exploit LLMs for document forgery, synthetic identity creation, logistics planning, or disinformation campaigns. Existing studies often highlight such risks in theory, yet few provide systematic empirical evidence of how state-of-the-art LLMs can be exploited. This paper introduces the Silent Adversary Framework (SAF), a structured pipeline that models the sequential stages by which obfuscated prompts can covertly bypass safeguards. We evaluate ten high-risk scenarios using five leading models—GPT-4o, Claude 3.7 Sonnet, Gemini 2.5 Flash, Grok 3, and Runway Gen-2—and assess outputs through three standardized metrics: Bypass Success Rate (BSR), Output Realism Score (ORS), and Operational Risk Level (ORL). Results reveal that, while all models exhibited some susceptibility, vulnerabilities were heterogeneous. Claude showed greater resistance in chemistry-related prompts, whereas GPT-4o and Gemini generated highly realistic outputs in identity fraud and logistics optimization tasks. Document forgery attempts produced only partially successful templates that lacked critical security features. These findings highlight the uneven distribution of risks across models and domains. By combining a reproducible adversarial framework with empirical testing, this study advances the evidence base on LLM misuse and provides actionable insights for policymakers and border security agencies, underscoring the need for stronger safeguards and oversight in the deployment of generative AI.
- Open Access
- 11 August 2025
- Published by MDPI AG in Preprints.org
Emerging Threat Vectors: How Malicious Actors Exploit LLMs to Undermine Border Security
The rapid proliferation of Large Language Models (LLMs) has dramatically advanced natural language processing (NLP), unlocking unprecedented capabilities in language generation, reasoning, and autonomous decision support. While these systems have enabled remarkable innovation, their widespread release as free and publicly accessible tools through open platforms has simultaneously introduced a new class of security vulnerabilities. This study explores how malicious actors can exploit such openly available, free and in public platforms LLMs by leveraging benign-sounding prompts that strategically bypass ethical safeguards-a process known as jailbreaking LLMs. We introduce a structured exploitation pipeline framework—termed the Silent Adversary Framework—which captures the sequential phases of LLM misuse, from intent obfuscation to real-world operational deployment. This framework is designed not only to formalize the process of covert exploitation but also to surface the fundamental safety challenges posed by current-generation LLMs, particularly the inability of alignment mechanisms to detect contextually veiled malicious intent. Through empirical testing across ten high-risk scenarios—including document forgery, synthetic identity creation, border evasion logistics, disinformation scripting, and insider persuasion—we evaluate how multiple leading models respond to adversarial prompt engineering. These scenarios are grounded in real-world border security operations, offering concrete illustrations of how generative models could be weaponized in silent but strategic ways. The results reveal that even state-of-the-art LLMs remain susceptible to manipulation, especially when deployed offline or in lightly moderated environments—conditions increasingly common due to their unrestricted availability. By bridging experimental findings with operational risk analysis, this work contributes to the growing field of AI safety and policy. We conclude with recommendations for strengthening semantic safeguards, improving alignment protocols, and introducing usage regulations tailored to national security-sensitive domains.
- 11 August 2025
- Published by MDPI AG in Preprints.org
Open AccessEmerging Threat Vectors: How Malicious Actors Exploit LLMs to Undermine Border Security
The rapid proliferation of Large Language Models (LLMs) has dramatically advanced natural language processing (NLP), unlocking unprecedented capabilities in language generation, reasoning, and autonomous decision support. While these systems have enabled remarkable innovation, their widespread release as free and publicly accessible tools through open platforms has simultaneously introduced a new class of security vulnerabilities. This study explores how malicious actors can exploit such openly available, free and in public platforms LLMs by leveraging benign-sounding prompts that strategically bypass ethical safeguards-a process known as jailbreaking LLMs. We introduce a structured exploitation pipeline framework—termed the Silent Adversary Framework—which captures the sequential phases of LLM misuse, from intent obfuscation to real-world operational deployment. This framework is designed not only to formalize the process of covert exploitation but also to surface the fundamental safety challenges posed by current-generation LLMs, particularly the inability of alignment mechanisms to detect contextually veiled malicious intent. Through empirical testing across ten high-risk scenarios—including document forgery, synthetic identity creation, border evasion logistics, disinformation scripting, and insider persuasion—we evaluate how multiple leading models respond to adversarial prompt engineering. These scenarios are grounded in real-world border security operations, offering concrete illustrations of how generative models could be weaponized in silent but strategic ways. The results reveal that even state-of-the-art LLMs remain susceptible to manipulation, especially when deployed offline or in lightly moderated environments—conditions increasingly common due to their unrestricted availability. By bridging experimental findings with operational risk analysis, this work contributes to the growing field of AI safety and policy. We conclude with recommendations for strengthening semantic safeguards, improving alignment protocols, and introducing usage regulations tailored to national security-sensitive domains.