Mulong Luo

          Postdoctoral Research Fellow
          The University of Texas at Austin
          mulong AT utexas DOT edu

          Vita, Google Scholar, LinkedIn, Twitter

 

I am a postdoctoral research fellow at the University of Texas at Austin working with Mohit Tiwari. I recently graduated from the School of Electrical and Computer Engineering at Cornell University, advised by Edward Suh. My current research interests are the following:

• Using AI agents (e.g., reinforcement learning) for exploring the trustworthiness of computer systems;
• Trustworthiness of AI systems (LLMs, autonomous vehicles 1, 2, 3, and neural networks 4, 5, 6 ).

I aim to build future trustworthy (AI-oriented) computer systems with the help of AI.

I am on the job market for the 2024-2025 season looking for tenure-track positions and/or industry research positions. If you have job openings for researchers in the intersection of trustworthy systems and applied machine learning, please drop me an email at mulong@utexas.edu [Research Statement] [Teaching Statement]

News

• 2024/12, invited to the program committee of ACM CCS 2025, the paper registration deadline is Jan, 2nd, 2025, please consider submit your best work.
• 2024/11, gave a keynote talk at HASP @ MICRO 2024 on RL for microachitectural security, here are the slides.
• 2024/9, talk at SRC TECHCON on RL for eviction set finding.
• 2024/8, talk at DEFCON AI Village on ConfusedPilot.
• 2024/5, invited to the program committee of IEEE S&P 2025.
• 2024/4, organized a tutorial at ASPLOS 2024 on Learning-based Microachitectural Attack Detection.
• 2024/2, won best reviewer award at VehicleSec 2024.
• 2023/8, joined UT Austin as a postdoctoral reseacher.
• 2023/10, invited to the external review committee of ISCA 2024.
• 2023/7, invited to the program committee (light) of HPCA 2024.
• 2023/7, awarded $1,500 AWS credit for NSF-CISE Cloudbank for promoting reinforcement learning in computer system research.
• 2023/7, invited talk at DACPS@DAC 2023.
• 2023/6, organized a Tutorial at ISCA 2023 on Reinforcement Learning for Computer Systems
• 2023/6, selected as CPS Rising Star.
• 2023/5, MACTA is presented at ICLR 2023.
• 2023/4, invited to the program committee of Usenix Security 2024.
• 2023/2, presented AutoCAT at HPCA 2023.
• 2022/12, invited to the program committee of ACM CCS 2023.
• 2022/10, my paper selected as Top Ticks in Hardware and Embedded Security 2022 shortlist.
• 2020/8, presented at Usenix Security 2020 on autonomous vehicle security.
• 2018/11, my paper won best paper award at CPSSPC@CCS 2018.

Education

• Doctor of Philosophy, Computer Engineering, Cornell University, 2017-2023.

• Master of Science, Computer Science, University of California San Diego, 2017.

• Bachelor of Science, Microelectronics, Peking University, 2014.

Selected Publications

• S. Banerjee *, P. Sahu *, M. Luo, A. Valhdiek-Oberwager, N. J. Yadwadkar, M. Tiwari. “SoK: Attack and Defense on Compound AI”, in submission. (* Equal contribution.) preprint.

• A. RoyChowdhury*, M. Luo, et. al., “Confused Deputy Risks in RAG-based LLMs”, [pdf],[website].Security Magazine, Data Breach Today, CYBR Monk, Secure World.(* Undergrad student advised.)

• M. Luo, M. Tiwari. “Towards Reinforcement Learning for Eviction-Set Finding for Randomized Caches”,SRC TECHCON, 2024.

• J. Cui, X. Yang*, M. Luo*, G. Lee*, et. al., “MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection”, accepted to International Conference on Learning Representation (ICLR), 2023. [pdf] (* Equal contributions.),[code]

• M. Luo*, W. Xiong*, et. al., “AutoCAT: Reinforcement Learning for Automated Exploration of Cache Timing-Channel Attacks”, accepted to IEEE International Symposium on High Performance Computer Architecture (HPCA), 2023. [pdf][code](* Equal contributions.)

• M. Luo, G. E. Suh, “Accelerating Path Planning for Autonomous Driving with Hardware-assisted Memorization”, in International conference on Application-specific Systems, Architectures and Processors (ASAP), 2022. [pdf]

• M. Luo, G. E. Suh, “Interrupt Attack on TEE for Robotic Vehicles”, in Automobile and Autonomous Vehicle Security Workshop (AutoSec), 2022, collocated with Networked and Distributed System Symposium (NDSS). [pdf],[talk]

• M. Luo, A. C. Myers, G. E. Suh, “Stealthy Tracking of Autonomous Vehicles with Cache Side Channels”, in 29th USENIX Security Symposium, 2020, pp.859-876 [pdf] [slides][talk] (Shortlisted for Top Picks in Hardware and Embedded Security 2022.)

• J. H. Lin, X. Jiao, M. Luo, “Vulnerability of hardware neural networks to dynamic operation point variations”, in IEEE Design and Test, 2020. [pdf]

• J. Liu, J. C. Davies, A. Ferraiuolo, A. Ivanov, M. Luo, et al., “Secure Autonomous Cyber-Physical Systems Through Verifiable Information Flow Control”, in Workshop on Cyber-Physical Systems Security and PrivaCy (CPS-SPC), collocated with ACM Conference on Computer and Communications Security (CCS), 2018, pages 48-59 (Best Paper Award). [pdf]

• X. Jiao, M. Luo, J. H. Lin, R. K. Gupta, “An Assessment of Vulnerability of Hardware Neural Networks to Dynamic Voltage and Temperatrue Variations”, in Internaional Conference on Computer-Aided Design (ICCAD), 2017, 940-950. [pdf]

Tutorials

• M. Luo, et al., LDMA: Learning-based Detection of Microarchitectural Attacks, co-located with Architectural Support for Programming Languages and Operating Systems (ASPLOS), 2024.

• M. Luo, et al., Reinforcement Learning for Computer Architecture and Systems (RL4CAS) Tutorial, co-located with International Symposium on Computer Architecture (ISCA), 2023.

Invited Talks

• Reinforcement Learning for Microarchitectural Security: Cache Timing Channel, Speculative Execution, and Defense at The International Workshop on Hardware and Architectural Support for Security and Privacy (HASP), co-located with MICRO 2024.

• Reinforcement Learning for Automated Exploration and Detection of Cache-Timing Attacks in CPS Hardware at The Sixth International Workshop on Design Automation for Cyber-Physical Systems (DACPS), co-located with DAC 2023.

Services

• Selected Technical Program Committees:
  • Proposal Reviewer, NSF Security and Trustworthy CyberSpace (SaTC) 2.0 Program..
  • TPC, ACM Conference on Computer and Communications Security (CCS), 2023, 2025
  • TPC, IEEE Symposium on Security and Privacy, 2025.
  • TPC, USENIX Security Symposium, 2024.
  • ERC, International Symposium on Computer Architecture (ISCA), 2024.
  • lightPC, International Symposium on High-Performance Computer Architecture (HPCA), 2024.
  • TPC, International Symposium on Research in Attacks, Intrusions and Defenses (RAID), 2023, noteworthy reviewers.
  • TPC, USENIX Symposium on Vehicle Security and Privacy (VehicleSec), co-located with Symposium on Networked and Distributed System Security (NDSS), 2023, 2024, outstanding reviewer, [2025].
• Organization:
  • Publication Chair, ISOC Symposium on Vehicle Security and Privacy (VehicleSec), co-located with Symposium on Networked and Distributed System Security (NDSS), 2024.
  • Local Arrangement Chair, The International Workshop on Hardware and Architectural Support for Security and Privacy (HASP) 2024, co-located with International Symposium on Microarchitecture (MICRO), 2024.
  • Session Chairs, USENIX Security 2024, ML for security session, and Fault Attacks in ML session.

Teaching

I have been serving as a teaching assistant for multiple undergradudate and graduate-level courses at Cornell and UCSD.

• Head TA, ECE2300, Digital Logic and Computer Organization, 2020 Fall at Cornell by Prof. David Albonesi

• TA, ECE5770, Resilient Computer Systems, 2019, 2018 Fall at Cornell by Prof. Edward Suh

• Head TA, CSL140, Components and Design Techniques for Digital Systems, 2017 Spring at UCSD by Prof. C.K. Cheng

• Head TA, CSL140L, Digital Circuits Laboratory, 2017 Winter at UCSD by Prof. Rajesh Gupta and visiting Prof. Avind from MIT

Industry

• System on Chip (SoC) platform architecture intern, Qualcomm Inc., 2021.

• Software Reseach and Development Intern, Synopsys Inc., 2016.