Papers & Preprints

Selected Manuscripts

Concise summaries of first-author and collaborative research on inference-time antidistillation defenses against model extraction and theory-grounded evaluation across 34 LLMs and 198 human participants, with direct links to arXiv, PDFs, and open-source code.

2026

Preprints & Reviews

Click any paper title or arXiv link for the full manuscript and experimental plots.

arXiv:2610.41044 · Preprint · Under review · 2026

Consensus Within, Competition Between: Decentralized LLM Teams for Perimeter Defense

Khawaja Abaid Ullah, Ananya Acharya, Mohammad Javad Khojasteh

Demonstrated that decentralized LLM teams using an external auction-based conflict-resolution protocol (CBAA) achieve lower breach rates than centralized or independently acting teams, and built a reproducible testbed evaluating coordination under communication constraints, decision authority, and multimodal visual deception.

arXiv PDF Code

BibTeX

@misc{ullah2026consensus,
  title = {Consensus Within, Competition Between: Decentralized LLM Teams for Perimeter Defense},
  author = {Khawaja Abaid Ullah and Ananya Acharya and Mohammad Javad Khojasteh},
  year = {2026},
  eprint = {2610.41044},
  archivePrefix = {arXiv},
  primaryClass = {cs.MA},
  url = {https://arxiv.org/abs/2610.41044}
}

arXiv:2607.15467 · Under review · IEEE OJCS · 2026

ADS-C: Antidistillation Sampling for Classification

Khawaja Abaid Ullah, Mohammad Javad Khojasteh

Margin-aware inference-time defense against soft-label model extraction that preserves 100% of served top-1 predictions while reducing distilled-student accuracy by 29.6 pp on CIFAR-10, 17.4 pp on CIFAR-100, and 13.3 pp on Tiny-ImageNet.

arXiv PDF Code

BibTeX

@misc{ullah2026adsc,
  title = {ADS-C: Antidistillation Sampling for Classification},
  author = {Khawaja Abaid Ullah and Mohammad Javad Khojasteh},
  year = {2026},
  eprint = {2607.15467},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2607.15467}
}

Manuscript under review · 2026

AntidistillBench: A Unified Benchmark of Test-Time Antidistillation Defenses for Classification

Khawaja Abaid Ullah, Mohammad Javad Khojasteh

First-of-its-kind unified benchmark and matched-cost evaluation protocol for test-time antidistillation defenses in classification, comparing existing defenses under a common threat model for suppressing student distillation.

Companion Code (ADS-C)

BibTeX

@unpublished{ullah2026antidistillbench,
  title = {AntidistillBench: A Unified Benchmark of Test-Time Antidistillation Defenses for Classification},
  author = {Khawaja Abaid Ullah and Mohammad Javad Khojasteh},
  year = {2026},
  note = {Manuscript under review}
}

arXiv:2608.09717 · Under review · 2026

How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Persona Ratings Across Multiple LLMs and Humans

Hasan Mahmud, Khawaja Abaid Ullah, Mohammad Javad Khojasteh, Jamison Heard, Prabu David

Evaluated social-judgment reliability and human-LLM alignment across 34 large language models and 198 human participants using theory-grounded persona ratings and controlled analyses of gender presentation.

arXiv PDF Code

BibTeX

@misc{mahmud2026socialattraction,
  title = {How Do Large Language Models Judge Social Attraction? Evidence from Theory-Grounded Persona Ratings Across Multiple LLMs and Humans},
  author = {Hasan Mahmud and Khawaja Abaid Ullah and Mohammad Javad Khojasteh and Jamison Heard and Prabu David},
  year = {2026},
  eprint = {2608.09717},
  archivePrefix = {arXiv},
  primaryClass = {cs.CL},
  url = {https://arxiv.org/abs/2608.09717}
}