FORTIS Lab

FORTIS stands for Foundations Of Robust Trustworthy Intelligent Systems. Inspired by the Latin word fortis, meaning strong or resilient, the FORTIS Lab builds AI systems that emphasize robustness, trustworthiness, scalability, and open-source accessibility. The lab addresses core challenges such as anomaly detection, out-of-distribution (OOD) detection, and structured data modeling, while advancing methods in graph learning and generative AI to create practical impact across domains like science, finance, and societal decision-making.

1. PhD Openings and Application Guidelines I will recruit 1 Ph.D. student for Fall 2026. We also have openings for undergraduate and graduate interns all the time, both at USC and elsewhere (preferably in North America for time zone compatibility).

• Research Focus: Candidates should align with my core research areas. For details, please visit my research interests.
  Update (2025–2026): For Fall 2026, I am only recruiting Ph.D. students whose interests align with a new research direction combining anomaly / out-of-distribution detection, crypto systems, and LLMs or distributed AI infrastructures. This includes but is not limited to (these are just examples):
  • Verifiable anomaly detection in blockchain-based AI inference
  • Distributed OOD detection among multi-agent LLM systems
  • Anomaly-aware tokenomics and incentive design
  Candidates with system or crypto backgrounds (e.g., Cosmos SDK, EVM, ZK, consensus protocols) are especially encouraged to apply.
• Prerequisites for Ph.D.: Successful candidates typically have:
  • Multiple published, relevant top-tier publications in ML (e.g., NeurIPS, ICML, ICLR), Systems (e.g., MLSys, VLDB, OSDI), or LLMs (ACL, EMNLP, NAACL). This list is not exhaustive.
  • Strong programming skills, demonstrated through research projects or significant open-source contributions.
• Prerequisites for Research Interns: Successful candidates typically have:
  • At least one top-tier publication in ML (e.g., NeurIPS, ICML, ICLR), Systems (e.g., MLSys, VLDB, OSDI), or LLMs (ACL, EMNLP, NAACL). This list is not exhaustive.
  • Strong programming skills, demonstrated through research projects or significant open-source contributions.
  • I do not have any summer interns -- I am also enjoying summer for fun :)

2. Email for Connection and Form Submission - For all positions, please fill out this Google Form: Application Form and also email the following details (subject line: "Interested in PhD/Intern at Fall 26"): Magic Words - please include Trojan in the email title to demonstrate that you have read these instructions carefully.

• CV: Provide a concise summary of your background and your future plans.
• Why FORTIS?: Mention any of my research papers or topics that have caught your interest. Additionally, feel free to propose new topics you are interested in exploring. I am always open to innovative ideas and fresh perspectives.

3. Compensation. Ph.D. students will receive the full support (tuition waiver + stipend is $40,000 in 2024-25) outlined by the CS department. TA is always guaranteed, and we will try to give you as many RA as possible. We do not have paid opportunities for undergraduate and master RA; it is not allowed to pay remote interns at USC :( Please consider this before reaching out.

4.1. GPU Clusters. In November 2023, we deployed fortis-prima, a high-performance GPU server equipped with dual AMD EPYC 7763 ("Milan") CPUs, 1 TB DDR4 memory (64×16 GB), 15 TB SSD storage, and 8× NVIDIA RTX 6000 Ada GPUs (released Q4 2022; up to 1.5× faster than the previous A6000 Ampere). In Fall 2025, we are deploying fortis-nova, a second GPU server with support for 8× NVIDIA RTX 6000 Blackwell Max-Q GPUs (96 GB each, released in 2025). It will launch with 4 GPUs installed, and the remaining 4 will be added in 2026 to complete the full 8-GPU configuration.

4.2. Cloud Credits. We recently (Aug 2024) get $20,000 AWS credit; thank you, Amazon.