Hongxin Hu
Professor and Associate Chair, Department of Computer Science and Engineering
Director, Center of Excellence in Information Systems Assurance Research and Education

University at Buffalo
The State University of New York (SUNY)

Office: 311 Davis Hall, Buffalo, NY 14260
Email: hongxinh@buffalo.edu
Photo: Hongxin Hu
Quick Links: [ Research | Publications | Teams | Teaching | Awards | Services ]
Short Bio

I am a Professor and Associate Chair in the Department of Computer Science and Engineering at University at Buffalo, SUNY. I also serve as Director of the Center of Excellence in Information Systems Assurance Research and Education (CEISARE) and Associate Director for AI and Security at the Institute for Artificial Intelligence and Data Science (IAD).

My research operates at the intersection of cybersecurity, machine learning, and networking. Reflecting this interdisciplinary focus, I have published extensively across top venues in cybersecurity (S&P, CCS, USENIX Security, NDSS), machine learning (NeurIPS, ICML, EMNLP), networking (SIGCOMM, NSDI), and human-computer interaction (CHI, CSCW). My work has been supported by federal and industry grants from the NSF (including SaTC, CNS, IIS, OAC, and SOC), USDOT, Amazon, Google, IBM, and others.

I am a recipient of the NSF CAREER Award (2019), the Amazon Research Award (2022), the ACM SACMAT Test-of-Time Award (2024), the IEEE Big Data Security Senior Research Award (2025), and UB’s Exceptional Scholar Award – Sustained Achievement (2026). My papers have received Best/Distinguished Paper Awards at ACM ASIACCS (2022), ACSAC (2020), IEEE ICC (2020), ACM SIGCSE (2018), and ACM CODASPY (2014), as well as First Place in the ACM SIGCOMM 2018 Student Research Competition. Additionally, my research has been recognized by the Global System for Mobile Communications Association (GSMA), featured by the IEEE Special Technical Community on Social Networking, and covered by major media outlets including ACM TechNews, InformationWeek, Slashdot, and NetworkWorld.

News
  • 09/2026 [Paper]: Our paper "Correct in Isolation, Broken in Translation: Exploiting Cross-Schema Vulnerabilities in LTE and 5G Base Stationsn" has been accepted to S&P 2027.
  • 09/2026 [Paper]: Our paper "AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification" has been accepted to NDSS 2027.
  • 08/2026 [Paper]: Our paper "DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents" has been accepted to EMNLP 2026.
  • 06/2026 [Talk]: Our talk "The Compiler That Can’t Read: Crashing Every 5G Phone With One Byte" has been accepted to DEF CON 34.
  • 06/2026 [Paper]: Our paper "MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration" has been accepted to CCS 2026.
  • 01/2026 [Paper]: Our paper "Beyond Age-Based Restrictions: Rethinking Children's Online Safety Through Comparing Parent–Child Perspectives of Risks in User-Generated Content Games" has been accepted to CHI 2026.
  • 12/2025 [Paper]: Our paper "Semantics Over Syntax: Uncovering Pre-Authentication 5G Baseband Vulnerabilities" has been accepted to USENIX Security 2026. MediaTek has assigned 3 high-severity CVEs (CVE-2025-20666, CVE-2025-20644, and CVE-2025-20703) to this work. The confirmed vulnerabilities affect 64 chipset models and over 542 commercially available smartphone models. CSMA has also acknowledged our disclosure by assigning a CVD ID (CVD-2025-0110). This work has been featured by UBNow as well.
  • 08/2025 [Paper]: Our paper "HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection" has been accepted to EMNLP 2025.
  • 05/2025 [Senior Research Award]: I am honored to be the recipient of the 2025 IEEE Big Data Security Senior Research Award.
  • 02/2025 [Paper]: Our paper "Towards LLM-Assisted Vulnerability Detection and Repair for Open-Source 5G UE Implementations" has been accepted to FutureG 2025.
  • 02/2025 [Paper]: Our paper "From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning" has been accepted to CVPR 2025.
  • 01/2025 [Paper]: Our paper "APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching" has been accepted to USENIX Security 2025.
  • 01/2025 [Paper]: Our paper "JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation" has been accepted to USENIX Security 2025.
  • 09/2024 [Paper]: Our paper "I know what you MEME! Understanding and Detecting Harmful Memes with Multimodal Large Language Models" has been accepted to NDSS 2025.
  • 07/2024 [Paper]: Our paper "Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks" has been accepted to CCS 2024.
  • 07/2024 [Paper]: Our paper "A First Look at Security and Privacy Risks in the RapidAPI Ecosystem" has been accepted to CCS 2024.
  • 05/2024 [Test-of-Time Award]: Our paper "Game Theoretic Analysis of Multiparty Access Control in Online Social Networks", published in SACMAT 2014, has been selected for the 2024 ACM SACMAT Test-of-Time Award.
  • 03/2024 [Paper]: Our paper "Moderating Illicit Online Image Promotion for Unsafe User Generated Content Games Using Large Vision Language Models" has been accepted to USENIX Security 2024.
  • 02/2024 [Paper]: Our paper "A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning" has been accepted to CVPR 2024.
  • 01/2024 [Paper]: Our paper "Understanding GDPR Non-Compliance in Privacy Policies of Alexa Skills in European Marketplaces" has been accepted to WWW 2024.
Research Interests
Selected and Recent Publications [Google Scholar] [All Publications]
  • Correct in Isolation, Broken in Translation: Exploiting Cross-Schema Vulnerabilities in LTE and 5G Base Stations
    Qiqing Huang, Xingyu Wang, Xiaofeng Chen, Hongxin Hu
    In Proceedings of the 48th IEEE Symposium on Security and Privacy (S&P 2027), Montreal, Canada, May 17-19, 2027.
  • AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
    Tian Zhang, Yiwei Xu, Juan Wang, Keyan Guo, Xiaoyang Xu, Bowen Xiao, Quanlong Guan, Jinlin Fan, Jiawei Liu, Zhiquan Liu, Hongxin Hu
    In Proceedings of the Network and Distributed System Security Symposium (NDSS 2027), Seoul, Republic of Korea, March 22 –26, 2027.
  • DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents
    Rupam Patir, Keyan Guo, Suvadra Barua, Jiawei Guo, Abhijeet Pathak, Dinesh Gudimetla, Hongxin Hu, Haipeng Cai
    In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP 2026), Findings, Budapest, Hungary, October 24 –29, 2026.
  • MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration
    Shenyi Zhang, Keyan Guo, Zihao Wang, Xuebin Li, Lingchen Zhao, Hongxin Hu, Chao Shen, Qian Wang
    In Proceedings of ACM SIGSAC Conference on Computer and Communications Security (CCS 2026), The Hague, The Netherlands, November 15-19, 2026.
  • Semantics Over Syntax: Uncovering Pre-Authentication 5G Baseband Vulnerabilities [PDF]
    Qiqing Huang, Xingyu Wang, Wanda Guo, Guofei Gu, and Hongxin Hu
    In Proceedings of the 35th USENIX Security Symposium (USENIX Security 2026), Baltimore, MD, USA., August 13-14, 2026
  • Beyond Age-Based Restrictions: Rethinking Children's Online Safety Through Comparing Parent–Child Perspectives of Risks in User-Generated Content Games
    Ruchi Panchanadikar, Yang Hu, Keyan Guo, Amelia L Hall, Hongxin Hu, Nishant Vishwamitra, and Guo Freeman
    In Proceedings of the ACM CHI Conference on Human Factors in Computing Systems(CHI 2026), Barcelona, 13–17 April, 2026
  • APPATCH: Automated Adaptive Prompting Large Language Models for Real-World Software Vulnerability Patching
    Yu Nong, Haoran Yang, Long Cheng, Hongxin Hu, and Haipeng Cai
    In Proceedings of the 34th USENIX Security Symposium (USENIX Security 2025), Seattle, WA, USA, August 13-15, 2025
  • Jbshield: Defending large language models from jailbreak attacks through activated concept analysis and manipulation
    Shenyi Zhang, Yuchen Zhai, Keyan Guo, Hongxin Hu, Shengnan Guo, Zheng Fang, Lingchen Zhao, Chao Shen, Cong Wang, and Qian Wang
    In Proceedings of the 34th USENIX Security Symposium (USENIX Security 2025), Seattle, WA, USA, August 13-15, 2025
  • I know what you MEME! Understanding and Detecting Harmful Memes with Multimodal Large Language Models
    Yong Zhuang, Keyan Guo, Juan Wang, Yiheng Jing, Xiaoyang Xu, Wenzhe Yi, Mengda Yang, Bo Zhao, and Hongxin Hu
    In Proceedings of the Network and Distributed System Security Symposium (NDSS 2025), San Diego, CA, USA, February 24-28, 2025.
  • HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detection
    Yiheng Jing, Mingming Zhang, Yong Zhuang, Jiacheng Guo, Juan Wang, Xiaoyang Xu, Wenzhe Yi, Keyan Guo, Hongxin Hu
    In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), 2025
  • From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning
    Ziang Li, Hongguang Zhang, Juan Wang, Meihui Chen, Hongxin Hu, Wenzhe Yi, Xiaoyang Xu, Mengda Yang, and Chenjun Ma
    In Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR 2025), 2025
  • Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks
    Yu He, Boheng Li, Yao Wang, Mengda Yang, Juan Wang, Hongxin Hu, and Xingyu Zhao
    In Proceedings of ACM SIGSAC Conference on Computer and Communications Security (CCS 2024), Salt Lake City, USA, October 14-18, 2024.
  • A First Look at Security and Privacy Risks in the RapidAPI Ecosystem
    Song Liao, Long Cheng, Xiapu Luo, Zheng Song, Haipeng Cai, Danfeng (Daphne) Yao, and Hongxin Hu
    In Proceedings of ACM SIGSAC Conference on Computer and Communications Security (CCS 2024), Salt Lake City, USA, October 14-18, 2024.
  • End-Users Know Best: Identifying Undesired Behavior of Alexa Skills Through User Review Analysis
    Mohammed Aldeen, Jeffrey Young, Song Liao, Tsu-Yao Chang, Long Cheng, Haipeng Cai, Xiapu Luo, and Hongxin Hu
    In Proceedings of ACM Interactive, Mobile, Wearable, and Ubiquitous Technologies (UbiComp 2024), Melbourne, Australia, October 5-9, 2024.
  • Moderating Illicit Online Image Promotion for Unsafe User Generated Content Games Using Large Vision Language Models [PDF]
    Keyan Guo, Ayush Utkarsh, Wenbo Ding, Isabelle Ondracek, Ziming Zhao, Guo Freeman, Nishant Vishwamitra and Hongxin Hu
    In Proceedings of the 33rd USENIX Security Symposium (USENIX Security 2024), Philadelphia, PA, USA, August 14-16, 2024
  • A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning
    Xiaoyang Xu, Mengda Yang, Wenzhe Yi, Ziang Li, Juan Wang, Hongxin Hu, Yong Zhuang and Yaxin Liu
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024), Seattle, WA, USA, June 17-21, 2024
    Acceptance rate: 23.6%
  • Understanding GDPR Non-Compliance in Privacy Policies of Alexa Skills in European Marketplaces
    Song Liao, Mohammed Aldeen, Jingwen Yan, Long Cheng, Xiapu Luo, Haipeng Cai and Hongxin Hu
    In Proceedings of the 2024 ACM Web Conference (WWW 2024), Singapore, May 13-17, 2024
  • Moderating New Waves of Online Hate with Chain-of-Thought Reasoning in Large Language Models [PDF]
    Nishant Vishwamitra, Keyan Guo, Farhan Tajwar Romit, Isabelle Ondracek, Long Cheng, Ziming Zhao and Hongxin Hu
    In Proceedings of the 45th IEEE Symposium on Security and Privacy (S&P 2024), San Francisco, CA, USA, May 20-23, 2024
  • Hairpin: Rethinking Packet Loss Recovery in Edge-based Interactive Video Streaming
    Zili Meng, Xiao Kong, Jing Chen, Bo Wang, Mingwei Xu, Rui Han, Honghao Liu, Venkat Arun, Hongxin Hu and Xue Wei
    In Proceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 2024), Santa Clara, CA, USA, April 16-18, 2024
Teaching
  • Fall 2026: CSE 4/565: Computer Security
  • Fall 2025: CSE 565: Computer Security
  • Fall 2024: CSE 565: Computer Security
  • Spring 2024: CSE 569: Network Security
  • Fall 2023: CSE 704 - Seminar: Machine Learning and Cybersecurity
  • Fall 2023: CSE 565: Computer Security
  • Spring 2023: CSE 702 - Seminar: Machine Learning and Cybersecurity
  • Fall 2022: CSE 489/589: Modern Network Concepts
  • Spring 2022: CSE 610 - Special Topic: Security in Emerging Cyber Physical Systems
  • Fall 2021: CSE 489/589: Modern Network Concepts
  • Spring 2021: CSE 707 - Seminar: Security in Emerging Computing and Networking Systems
  • Fall 2020: CPSC 8580 - Security in Emerging Computing and Networking Systems
  • Spring 2020: CPSC 8570 - Security in Advanced Networking Technologies
  • Fall 2019: CPSC 8580 - Security in Emerging Computing and Networking Systems
  • Spring 2019: CPSC 8570 - Security in Advanced Networking Technologies
  • Fall 2018: CPSC 8580 - Security in Emerging Computing and Networking Systems
  • Fall 2018: CPSC-4200/6200 - Computer Security Principles
  • Spring 2018: CPSC 8580 - Security in Emerging Computing and Networking Systems
  • Fall 2017: CPSC-4200/6200 - Computer Security Principles
  • Spring 2017: CPSC 8570 - Security in Advanced Networking Technologies
  • Fall 2016: CPSC-4200/6200 - Computer Security Principles
  • Fall 2016: CPSC 8580 - Security in Emerging Computing and Networking Systems
  • Spring 2016: CPSC 8810 - Advanced Networking and Security
  • Fall 2015: CPSC-4200/6200 - Computer Security Principles
  • Spring 2015: CPSC 8810 - Advanced Networking and Security
  • Fall 2014: CPSC 8810 - Security in Emerging Computing and Networking Systems
Awards and Recognition
  • UB’s Exceptional Scholar Award – Sustained Achievement, 2026
  • IEEE Big Data Security Senior Research Award, 2025
  • ACM SACMAT Test-of-Time Award, 2024
  • Outstanding Research Award, UB CSE Department, 2022
  • Best Paper Award, ACM ASIACCS, 2022
  • Amazon Faculty Research Award, 2022
  • Distinguished Paper Award, ACSAC, 2020
  • Best Paper Award, IEEE ICC, 2020
  • NSF CAREER Award, 2019
  • First Place, ACM SIGCOMM SRC, 2018
  • Best Paper Award, ACM SIGCSE, 2018
  • Dean's Faculty Fellows Award, CECAS, Clemson University, 2017
  • Best Paper Award Honorable Mention, ACM SACMAT, 2016
  • Best Paper Award Nominee, IEEE ICNP, 2015
  • Best Applied Security Paper Award TOP-10 Finalist, SCAW, 2015
  • Front Page News, Post and Courier, 2015
  • Third Place, Extreme SDN Innovation Challenge, 2015
  • Best Paper Award, ACM CODASPY, 2014
  • Featured Article, IEEE Special Technical Community on Social Networking (STCSN), 2013
  • Outstanding Ph.D. Student Finalist in Compter Science, ASU, 2012
  • ACSAC Conferenceship Award, ACSAC, 2011
  • Best Paper Award Nominee, ACM SACMAT, 2011
  • IBM PhD Fellowship Nominee, UNCC, 2008
Professional Activities

Associate Editor:

Guest Editor:

Program Chair:

Poster Chair:

Proceedings Chair:

Workshop Chair:

Publicity Chair:

Web Chair:

Technical Program Committee: