Research

Security & Trustworthiness of AI Systems

My research focuses on making AI systems traceable, auditable, and secure throughout their development and deployment. I study AI supply-chain security, model provenance, and vulnerability propagation across interconnected AI models and systems. Using graph-based methods, static analysis, and large-scale empirical studies, I investigate how AI artifacts evolve, how dependencies are established, and how security risks propagate across model lineages. My broader interests include agentic AI security and trustworthy, resource-efficient edge AI.

Publications & manuscripts

AI Supply-Chain Security and Model Provenance

Open model hubs such as Hugging Face now host millions of models. Each one may derive from a base model through fine-tuning, adapters, quantization, or merging, and depend on datasets and code from many sources. These relationships form a large and largely undocumented AI supply chain. Lineage declarations are often missing, incomplete, or inconsistent, which makes it hard to answer basic security questions: Where did this model come from? What does it inherit? Who is affected when an upstream model is found to be unsafe?

My research models this ecosystem as a graph and develops methods to characterize, audit, and recover model provenance at scale. Selected projects are outlined below.

HuggingGraph: Understanding the Supply Chain of LLM Ecosystem

ACM CIKM 2025

Built a heterogeneous graph of the Hugging Face LLM ecosystem with 402,654 entities and 462,524 relationships, capturing model derivation, fine-tuning, adapters, quantization, merging, and dataset dependencies.
Analyzed ecosystem structure, connectivity, and provenance gaps to enable graph-based AI supply-chain analysis.
Released public graph datasets, documentation, and a companion repository to support reproducibility.

ProvCode: Static Auditing of Provenance Carryover for Hugging Face Models

Under review, ICSE 2027

Developed static-analysis methods to check whether model repositories and their source code preserve upstream provenance claims.
Examined inconsistencies between declared and code-derived lineage across roughly 75,000 Hugging Face models.

ChainInfer: Graph-Based Model Provenance Inference

Under review, WWW

Investigates recovery of missing model-to-model lineage relationships using graph topology, repository metadata, and learned representations.
Aims to reconstruct hidden upstream dependencies that model cards and metadata fail to declare.

Large-Scale Model Lineage Analysis

Ongoing

Extended data collection and dependency extraction to about three million Hugging Face model records, studying missing, incomplete, and nonstandard lineage declarations across the broader ecosystem.

Vulnerability Propagation Across Model Derivatives

If a base model behaves unsafely, do its descendants inherit that behavior? Supply-chain security depends on understanding how vulnerabilities propagate through adaptation. This line of work runs controlled, large-scale experiments to measure whether security weaknesses persist, weaken, or amplify as models are fine-tuned, adapted, and compressed.

VulChain: AI Supply-Chain Vulnerability Propagation

Manuscript Revision in Progress

Designed controlled empirical evaluations to test whether unsafe behaviors, including package hallucination and insecure URL generation, persist through fine-tuning, adapter-based adaptation, and quantization.
Measured vulnerability persistence using matched prompts and validated detectors across base models and their derivatives.

ChronoResolve: Retrospective Artifact Resolution for Model Lineage

Research in Progress

Investigates the identification of historical upstream artifacts a model was derived from, using file hashes, configurations, weight signatures, and temporal evidence.
Aims to reduce lineage ambiguity to support reproducible provenance and security auditing.

Agentic and Multi-Agent AI Security

LLMs are increasingly deployed as autonomous agents that call tools, process multimodal inputs, and collaborate with other agents. This creates new attack surfaces: a single injected prompt can cross trust boundaries, spread between agents, and trigger unsafe real-world actions. My research builds systematic tools to expose these failures and defend against them at runtime.

AgentFuzz: Trace-Level Fuzzing for Prompt Spillover in LLM Multi-Agent Systems

IEEE ICMLA 2026

Developed a trace-level fuzzing framework to study how adversarial prompts spill over across interacting LLM agents.
Evaluated attack propagation across communication topologies, injection channels, and verification configurations to characterize security failures in multi-agent workflows.

IEEE ICTAI 2026 · Accepted, to appear

Developed a model-agnostic runtime verification framework that combines symbolic policy validation, cross-modal consistency checking, and knowledge–environment alignment.
Evaluated it on 240 adversarial scenarios across three LLM backbones, preventing 94.2% of unsafe actions.

Trustworthy and Resource-Efficient Edge AI

Deploying AI on edge devices means working with tight compute budgets and often low-quality inputs. This work develops lightweight, semantic-guided learning methods that keep visual recognition robust and reliable under these constraints.

LiteAugNet: Lightweight Semantic-Guided Augmentation for Edge-Level Image Classification

ICPR 2026

A lightweight semantic-guided augmentation network that improves low-resolution image classification while respecting the compute limits of edge environments.

SEGA-Net: LLM-Guided Semantic-Enhanced GAN Augmentation for Low-Resolution Image Classification

IEEE AIxDKE 2026

Combines LLM-guided semantic augmentation with generative image synthesis to improve low-resolution visual recognition.

LiteAdapt: Adaptive Semantic Augmentation for Resource-Constrained Edge Environments

Journal Manuscript in Preparation

Extends semantic-guided augmentation with reliability-aware sample weighting, adaptive verification, and dynamic resource allocation.

SEGA-COM: Semantic-Reliability-Aware Generative Communication and Energy Allocation

Under review, ICC 2027

Brings semantic-reliability awareness to generative communication and energy allocation.

Applied Security Research

Alongside AI security, I work on practical vulnerability assessment for high-performance and containerized infrastructure.

Beyond CVSS: Context-Aware Exploitability Assessment of Vulnerabilities in HPC Containers

IEEE Cloud Summit 2026

Assesses vulnerability exploitability in HPC containers using deployment context, going beyond generic CVSS severity scores.