Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Phan The Duy

Phan The Duy

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

Crypto×4ML×1

Frequent co-authors

Van-Hau Pham4×
Khoa Ngo-Khanh1×
Nguyen Huu Quyen1×
Minh-Dai Tran-Duong1×
Nguyen Hai Phong1×
Nguyen Chi Thanh1×

Research Timeline

2026
Red-MIRROR: Agentic LLM-based Autonomous Penetration Testing with Reflective Verification and Knowledge-augmented Interaction

Red-MIRROR is a novel multi-agent LLM system that automates complex web penetration testing by integrating a memory-reflection backbone, achieving superior performance on industry benchmarks.

ORACAL: A Robust and Explainable Multimodal Framework for Smart Contract Vulnerability Detection with Causal Graph Enrichment

ORACAL, a novel multimodal framework, achieves state-of-the-art smart contract vulnerability detection by integrating control, data, and call graphs with causal reasoning and LLM-enhanced explainability.

ContractShield: Bridging Semantic-Structural Gaps via Hierarchical Cross-Modal Fusion for Multi-Label Vulnerability Detection in Obfuscated Smart Contracts

ContractShield is a robust multimodal framework that uses a novel three-level fusion mechanism to accurately detect multiple types of vulnerabilities in obfuscated smart contracts, significantly outperforming existing methods under adversarial conditions.

PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy

PoC-Adapt is an end-to-end framework that significantly improves the reliability and efficiency of automated vulnerability exploitation by integrating semantic state validation and reinforcement learning-driven policy adaptation.

Highlighted terms show continued research focus across papers

Papers

cs.CRRecentApr 8, 2026

PoC-Adapt: Semantic-Aware Automated Vulnerability Reproduction with LLM Multi-Agents and Reinforcement Learning-Driven Adaptive Policy

Phan The Duy, Khoa Ngo-Khanh, Nguyen Huu Quyen, Van-Hau Pham

PoC-Adapt is an end-to-end framework that significantly improves the reliability and efficiency of automated vulnerability exploitation by integrating semantic state validation and reinforcement learn…

View →
cs.CRRecentApr 3, 2026

ContractShield: Bridging Semantic-Structural Gaps via Hierarchical Cross-Modal Fusion for Multi-Label Vulnerability Detection in Obfuscated Smart Contracts

Minh-Dai Tran-Duong, Nguyen Hai Phong, Nguyen Chi Thanh, Doan Minh Trung +3 more

ContractShield is a robust multimodal framework that uses a novel three-level fusion mechanism to accurately detect multiple types of vulnerabilities in obfuscated smart contracts, significantly outpe…

View →
cs.LGcs.CRRecentMar 30, 2026

ORACAL: A Robust and Explainable Multimodal Framework for Smart Contract Vulnerability Detection with Causal Graph Enrichment

Tran Duong Minh Dai, Triet Huynh Minh Le, M. Ali Babar, Van-Hau Pham +1 more

ORACAL, a novel multimodal framework, achieves state-of-the-art smart contract vulnerability detection by integrating control, data, and call graphs with causal reasoning and LLM-enhanced explainabili…

View →
cs.CRRecentMar 28, 2026

Red-MIRROR: Agentic LLM-based Autonomous Penetration Testing with Reflective Verification and Knowledge-augmented Interaction

Tran Vy Khang, Nguyen Dang Nguyen Khang, Nghi Hoang Khoa, Do Thi Thu Hien +2 more

Red-MIRROR is a novel multi-agent LLM system that automates complex web penetration testing by integrating a memory-reflection backbone, achieving superior performance on industry benchmarks.

View →