Institution profile

Middle Tennessee State University

Academic institutionnorthamerica · us
Official website
Research library8linked papers
Opportunities0open roles
Selected work

Representative Papers

Distributed Quantum-Assisted Robust AoII Minimization in Satellite-Ground Integrated Edge Networks

Oct 05, 2026

This study addresses the inaccuracy of edge node state estimation caused by link outages in Space-Air-Ground Integrated Networks (SAGIN), where traditional Age of Information (AoI) fails to distinguish benign delays from hazardous errors. We propose SENTINEL, a distributed hybrid quantum-classical framework that introduces the Age of Incorrect Information (AoII) metric and formulates the first network-level AoII minimization model for multi-node SAGIN. By decomposing update intervals for closed-form cost computation, the framework jointly optimizes update rates, satellite-ground associations, and bandwidth allocation via QUBO modeling, Ising mapping, distributed QAOA, and ADMM mechanisms. Simulations demonstrate that SENTINEL outperforms learning-based baselines, matches optimal policies in small-scale networks while approximating exact minimax references, and provides rigorous worst-case AoII safety guarantees under complete outage scenarios.

0 citationsRead paper

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs

Aug 11, 2026

This work addresses the challenge of detecting backdoors in fine-tuned large language models under black-box settings—particularly when training data, clean reference models, or known trigger tokens are unavailable. The authors propose a “self-feeding” detection method that iteratively feeds a model’s own output back as its next input, progressively steering generated text toward the distribution of the fine-tuning data and thereby revealing latent backdoor behaviors. This approach is the first to systematically exploit an output-to-input feedback mechanism for efficient, internal-information-free triggering. Evaluated across six open-source models (3B–15B parameters) and eleven backdoor attack variants, the method achieves a model-level detection precision of 92.0%, maintains 100% precision within just four inference steps, and reduces query counts by 60%, demonstrating its effectiveness even under low single-prompt recall conditions.

0 citationsRead paper

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

Aug 11, 2026

This study addresses the critical security gap in large language model (LLM)-based autonomous agents endowed with real-world operational capabilities, where reasoning components remain highly vulnerable to attacks that can trigger unauthorized access, irreversible state changes, or cascading failures. Conducting a systematic literature review of 85 studies from 2023–2025 following PRISMA 2020 guidelines, this work reveals a pronounced imbalance between attack and defense research (3.9:1) and introduces the first four-layer vulnerability taxonomy for agent LLMs—encompassing perception, cognition, action, and interaction—identifying 13 vulnerability types and seven open challenges centered on isolation. Notably, perception-layer vulnerabilities account for 66% of reported issues, whereas high-risk action-layer threats such as tool misuse and sandbox escape constitute only 4.7%, highlighting a severe misalignment between research focus and actual risk. The study further identifies cross-layer vulnerability propagation due to architectural coupling as the root cause of systemic security weaknesses.

0 citationsRead paper
Recent publications

Latest Papers

Distributed Quantum-Assisted Robust AoII Minimization in Satellite-Ground Integrated Edge Networks

Oct 05, 2026

This study addresses the inaccuracy of edge node state estimation caused by link outages in Space-Air-Ground Integrated Networks (SAGIN), where traditional Age of Information (AoI) fails to distinguish benign delays from hazardous errors. We propose SENTINEL, a distributed hybrid quantum-classical framework that introduces the Age of Incorrect Information (AoII) metric and formulates the first network-level AoII minimization model for multi-node SAGIN. By decomposing update intervals for closed-form cost computation, the framework jointly optimizes update rates, satellite-ground associations, and bandwidth allocation via QUBO modeling, Ising mapping, distributed QAOA, and ADMM mechanisms. Simulations demonstrate that SENTINEL outperforms learning-based baselines, matches optimal policies in small-scale networks while approximating exact minimax references, and provides rigorous worst-case AoII safety guarantees under complete outage scenarios.

0 citationsRead paper

An Empirical Study of Output-to-Input Loops for Black-Box Backdoor Detection in Fine-Tuned Open-Weight LLMs

Aug 11, 2026

This work addresses the challenge of detecting backdoors in fine-tuned large language models under black-box settings—particularly when training data, clean reference models, or known trigger tokens are unavailable. The authors propose a “self-feeding” detection method that iteratively feeds a model’s own output back as its next input, progressively steering generated text toward the distribution of the fine-tuning data and thereby revealing latent backdoor behaviors. This approach is the first to systematically exploit an output-to-input feedback mechanism for efficient, internal-information-free triggering. Evaluated across six open-source models (3B–15B parameters) and eleven backdoor attack variants, the method achieves a model-level detection precision of 92.0%, maintains 100% precision within just four inference steps, and reduces query counts by 60%, demonstrating its effectiveness even under low single-prompt recall conditions.

0 citationsRead paper

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

Aug 11, 2026

This study addresses the critical security gap in large language model (LLM)-based autonomous agents endowed with real-world operational capabilities, where reasoning components remain highly vulnerable to attacks that can trigger unauthorized access, irreversible state changes, or cascading failures. Conducting a systematic literature review of 85 studies from 2023–2025 following PRISMA 2020 guidelines, this work reveals a pronounced imbalance between attack and defense research (3.9:1) and introduces the first four-layer vulnerability taxonomy for agent LLMs—encompassing perception, cognition, action, and interaction—identifying 13 vulnerability types and seven open challenges centered on isolation. Notably, perception-layer vulnerabilities account for 66% of reported issues, whereas high-risk action-layer threats such as tool misuse and sandbox escape constitute only 4.7%, highlighting a severe misalignment between research focus and actual risk. The study further identifies cross-layer vulnerability propagation due to architectural coupling as the root cause of systemic security weaknesses.

0 citationsRead paper