Rayhanur Rahman
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rayhanur Rahman has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Ahmed Ryan
PhD Research Student, University of Alabama, USA
2 shared publications - Erfan
PhD Research Student, University of Alabama, USA
2 shared publications Akond Ashfaque Ur Rahman
Dept. of Computer Science & Software Eng Auburn University Auburn AL USA
1 shared publication- Brandon Wroblewski
North Carolina State University, Raleigh, USA
1 shared publication - Brantley Morgan
North Carolina State University, Raleigh, USA
1 shared publication Junaid Mansur Ifti
Institute of Information Technology University of Dhaka Dhaka Bangladesh
1 shared publication
Latest Publications
- Open Access
- 13 August 2026
- Published by MDPI AG in Preprints.org
Agentic AI for Cyber Defense: A Survey of Failure Modes, Applications, and Research Opportunities
Modern agentic systems that plan, reason, invoke tools, and self-reflect offer a promising path to autonomous cyber defense and SOC analyst augmentation. Yet this same autonomy introduces novel failure modes and attack surfaces absent from traditional security pipelines. Despite rapid adoption, prior surveys remain fragmented: addressing agentic safety domain-agnostically, focusing on offensive use, or examining pre-agentic LLM-based defense in isolation, leaving the field without a structured, defense-focused framework integrating failure characterization, operational lifecycle mapping, and compliance alignment. This survey closes that gap through four analytical artefacts: a four-category failure taxonomy (natural, system, adversarial, compliance) spanning 22 subcategories and 94 failure modes with mitigations; a decomposition of defensive cybersecurity into 13 tasks classified by autonomy level, oversight regime, and failure exposure; a review of 22 research systems and 10 commercial offerings across five operational categories; and a catalogue of 20 governance gaps mapped to GDPR, EU AI Act, NIST AI RMF, ISO 42001, and sector-specific frameworks. We argue the autonomy ceiling is bounded asymmetrically, not by reasoning capability but by action irreversibility, mitigation maturity, and compliance envelope, and consolidate open challenges into eight research directions.
- 13 August 2026
- Published by MDPI AG in Preprints.org
Open AccessAgentic AI for Cyber Defense: A Survey of Failure Modes, Applications, and Research Opportunities
Modern agentic systems that plan, reason, invoke tools, and self-reflect offer a promising path to autonomous cyber defense and SOC analyst augmentation. Yet this same autonomy introduces novel failure modes and attack surfaces absent from traditional security pipelines. Despite rapid adoption, prior surveys remain fragmented: addressing agentic safety domain-agnostically, focusing on offensive use, or examining pre-agentic LLM-based defense in isolation, leaving the field without a structured, defense-focused framework integrating failure characterization, operational lifecycle mapping, and compliance alignment. This survey closes that gap through four analytical artefacts: a four-category failure taxonomy (natural, system, adversarial, compliance) spanning 22 subcategories and 94 failure modes with mitigations; a decomposition of defensive cybersecurity into 13 tasks classified by autonomy level, oversight regime, and failure exposure; a review of 22 research systems and 10 commercial offerings across five operational categories; and a catalogue of 20 governance gaps mapped to GDPR, EU AI Act, NIST AI RMF, ISO 42001, and sector-specific frameworks. We argue the autonomy ceiling is bounded asymmetrically, not by reasoning capability but by action irreversibility, mitigation maturity, and compliance envelope, and consolidate open challenges into eight research directions.
- Open Access
- 24 April 2026
- Published by MDPI AG in Preprints.org
From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification
Large Language Models (LLMs) show promise in automated software engineering, yet their guarantee of correctness is frequently undermined by erroneous or hallucinated code. To enforce model honesty, formal verification requires LLMs to synthesize implementation logic alongside formal specifications that are subsequently proven correct by a mathematical verifier. However, the transition from informal natural language to precise formal specification remains an arduous task. Our work addresses this by providing the NaturalLanguage2VerifiedCode (NL2VC)-60 dataset: a collection of 60 complex algorithmic problems. We evaluate 11 randomly selected problem sets across seven open-weight LLMs using a tiered prompting strategy: contextless prompts, signature prompts providing structural anchors, and self-healing prompts utilizing iterative feedback from the Dafny verifier. To address vacuous verification, where models satisfy verifiers with trivial specifications, we integrate the uDebug platform to ensure functional validation. Our results show that while contextless prompting leads to near-universal failure, structural signatures and iterative self-healing facilitate a dramatic performance turnaround. Specifically, Gemma 4-31B achieved a 90.91% verification success rate, while GPT-OSS 120B rose from zero to 81.82% success with signature-guided feedback. These findings indicate that formal verification is now attainable for open-weight LLMs, which serve as effective apprentices for synthesizing complex annotations and facilitating high-assurance software development.
- 24 April 2026
- Published by MDPI AG in Preprints.org
Open AccessFrom Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification
Large Language Models (LLMs) show promise in automated software engineering, yet their guarantee of correctness is frequently undermined by erroneous or hallucinated code. To enforce model honesty, formal verification requires LLMs to synthesize implementation logic alongside formal specifications that are subsequently proven correct by a mathematical verifier. However, the transition from informal natural language to precise formal specification remains an arduous task. Our work addresses this by providing the NaturalLanguage2VerifiedCode (NL2VC)-60 dataset: a collection of 60 complex algorithmic problems. We evaluate 11 randomly selected problem sets across seven open-weight LLMs using a tiered prompting strategy: contextless prompts, signature prompts providing structural anchors, and self-healing prompts utilizing iterative feedback from the Dafny verifier. To address vacuous verification, where models satisfy verifiers with trivial specifications, we integrate the uDebug platform to ensure functional validation. Our results show that while contextless prompting leads to near-universal failure, structural signatures and iterative self-healing facilitate a dramatic performance turnaround. Specifically, Gemma 4-31B achieved a 90.91% verification success rate, while GPT-OSS 120B rose from zero to 81.82% success with signature-guided feedback. These findings indicate that formal verification is now attainable for open-weight LLMs, which serve as effective apprentices for synthesizing complex annotations and facilitating high-assurance software development.
- Open Access
Unveiling Malicious Logic: Towards a Statement-Level Taxonomy and Dataset for Securing Python Packages
The widespread adoption of open-source ecosystems enables developers to integrate third-party packages, but also exposes them to malicious packages crafted to execute harmful behavior via public repositories such as PyPI. Existing datasets (e.g., pypi-malregistry, DataDog, OpenSSF, MalwareBench) label packages as malicious or benign at the package level, but do not specify which statements implement malicious behavior. This coarse granularity limits research and practice: models cannot be trained to localize malicious code, detectors cannot justify alerts with code-level evidence, and analysts cannot systematically study recurring malicious indicators or attack chains. To address this gap, we construct a statement-level dataset of 370 malicious Python packages (833 files, 90,527 lines) with 2,962 labeled occurrences of malicious indicators. From these annotations, we derive a fine-grained taxonomy of 47 malicious indicators across 7 types that capture how adversarial behavior is implemented in code, and we apply sequential pattern mining to uncover recurring indicator sequences that characterize common attack workflows. Our contribution enables explainable, behavior-centric detection and supports both semantic-aware model training and practical heuristics for strengthening software supply-chain defenses.
Open AccessUnveiling Malicious Logic: Towards a Statement-Level Taxonomy and Dataset for Securing Python Packages
The widespread adoption of open-source ecosystems enables developers to integrate third-party packages, but also exposes them to malicious packages crafted to execute harmful behavior via public repositories such as PyPI. Existing datasets (e.g., pypi-malregistry, DataDog, OpenSSF, MalwareBench) label packages as malicious or benign at the package level, but do not specify which statements implement malicious behavior. This coarse granularity limits research and practice: models cannot be trained to localize malicious code, detectors cannot justify alerts with code-level evidence, and analysts cannot systematically study recurring malicious indicators or attack chains. To address this gap, we construct a statement-level dataset of 370 malicious Python packages (833 files, 90,527 lines) with 2,962 labeled occurrences of malicious indicators. From these annotations, we derive a fine-grained taxonomy of 47 malicious indicators across 7 types that capture how adversarial behavior is implemented in code, and we apply sequential pattern mining to uncover recurring indicator sequences that characterize common attack workflows. Our contribution enables explainable, behavior-centric detection and supports both semantic-aware model training and practical heuristics for strengthening software supply-chain defenses.
- Open Access
- 22 July 2025
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 67 (10) , 8941-8981
Mining temporal attack patterns from cyberthreat intelligence reports
Cyberthreat intelligence (CTI) reports on past cyberattacks describe the sequence of actions of attackers in terms of time. The sequence contains temporal relations among attack actions, such as a malware is first downloaded and then executed. Information related to temporal relations enables cybersecurity practitioners to investigate past cyberattack incidents and analyze attackers’ behavior. However, cybersecurity practitioners must extract such information automatically, in a structured manner, through a common vocabulary to reduce human effort and enable sharing, and collaboration. The goal of this paper is to aid security practitioners in proactive defense against attacks by automatic information extraction of temporal relations among attack actions from cyberthreat intelligence reports. We propose ChronoCTI, an automated pipeline for extracting temporal relations among attack actions from CTI reports. The attack actions are represented as MITRE ATT&CK techniques, and the relations are represented as a knowledge graph. To construct ChronoCTI, we build a ground truth dataset of temporal relations and apply large language models, natural language processing, and machine learning techniques. ChronoCTI demonstrates higher precision but lower recall performance on a real-world dataset of 94 CTI reports. We apply ChronoCTI on a set of 713 CTI reports, where we identify 9 categories of temporal attack patterns consisting of 124 temporal attack patterns. We identify that the most prevalent pattern category is to trick victim users into executing malicious code to initiate the attack, followed by bypassing the anti-malware system in the victim software systems. Based on the observed patterns, we advocate for training users about cybersecurity best practices, introducing appropriate warning messages for end-users, introducing immutable operating systems, and enforcing multi-user authentications. Moreover, we advocate that practitioners leverage the automated mining capability of ChronoCTI and design countermeasures against recurring attack patterns.
- 22 July 2025
- Published by Springer Nature in Knowledge and Information Systems
- Vol. 67 (10) , 8941-8981
Open AccessMining temporal attack patterns from cyberthreat intelligence reports
Cyberthreat intelligence (CTI) reports on past cyberattacks describe the sequence of actions of attackers in terms of time. The sequence contains temporal relations among attack actions, such as a malware is first downloaded and then executed. Information related to temporal relations enables cybersecurity practitioners to investigate past cyberattack incidents and analyze attackers’ behavior. However, cybersecurity practitioners must extract such information automatically, in a structured manner, through a common vocabulary to reduce human effort and enable sharing, and collaboration. The goal of this paper is to aid security practitioners in proactive defense against attacks by automatic information extraction of temporal relations among attack actions from cyberthreat intelligence reports. We propose ChronoCTI, an automated pipeline for extracting temporal relations among attack actions from CTI reports. The attack actions are represented as MITRE ATT&CK techniques, and the relations are represented as a knowledge graph. To construct ChronoCTI, we build a ground truth dataset of temporal relations and apply large language models, natural language processing, and machine learning techniques. ChronoCTI demonstrates higher precision but lower recall performance on a real-world dataset of 94 CTI reports. We apply ChronoCTI on a set of 713 CTI reports, where we identify 9 categories of temporal attack patterns consisting of 124 temporal attack patterns. We identify that the most prevalent pattern category is to trick victim users into executing malicious code to initiate the attack, followed by bypassing the anti-malware system in the victim software systems. Based on the observed patterns, we advocate for training users about cybersecurity best practices, introducing appropriate warning messages for end-users, introducing immutable operating systems, and enforcing multi-user authentications. Moreover, we advocate that practitioners leverage the automated mining capability of ChronoCTI and design countermeasures against recurring attack patterns.