Publications

Code and data from our lab: github.com/peng-gao-lab

Underlined names denote students advised or mentored by me.

Preprints

• Kernel-Layer Runtime Defense for LLM Agents Against Indirect Prompt Injection
  Aravinda Kashyap, Basavesh Ammanaghatta Shivakumar, Chong Xiang, Danfeng (Daphne) Yao, Peng Gao
  Preprint, 2026
  
• NetAgent: Multi-Task Agentic Network Traffic Analysis Made Practical
  Hao Fu, Dawn Song, Peng Gao
  arXiv:2610.07386, 2026
  [paper]
• IDSForge: Self-Explaining Network Intrusion Detection Through Neural Behavioral Rule Learning
  Hao Fu, Jinxia Wei, Wan Wei, Chun Long, Degang Sun, Peng Gao
  arXiv:2610.38890, 2026
  [paper]
• SQLoom: Set-Contrastive Learning of Syntactic, Semantic, and Logical Dependencies for Text-to-SQL
  Hao Fu, Degang Sun, Wan Wei, Jinxia Wei, Chun Long, Peng Gao
  Preprint, 2026
  
• EndpointIR-Bench: Benchmarking Autonomous Agents in Endpoint Security Incident Investigation
  Dongxun Su, Juncheng Ye, Zikai Zhou, Peng Gao, Feng Dong, Jingmei Chen, Zixia Chen, Haoyu Wang
  Preprint, 2026
  
• BypassGym: A Benchmark for Evaluating AI Agents' Endpoint Defense Evasion Capabilities
  Weifeng Yuan, Zifan Chen, Yucheng Zhang, Feng Dong, Peng Gao
  Preprint, 2026
  
• From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage
  Saimon Amanuel Tsegai, Alex Kantchelian, Danfeng (Daphne) Yao, Peng Gao
  arXiv:2610.10608, 2026
  [paper]
• VulChain: Tracing Vulnerability Propagation along the LLM Supply Chain
  Mohammad Shahedur Rahman, Runbang Hu, Ruimin Sun, Peng Gao, Yuede Ji
  Preprint, 2026
  
• ValiAssist: Scaling LLM-generated Programming Feedback Validation by Demonstration
  Xiaohang Tang, Rehema Abulikemu, Peng Gao, Yan Chen
  arXiv:2610.27248, 2026
  [paper]
• Does Multi-Task Learning Work for Crystals? A Systematic Study and a Knowledge-Guided Mixture-of-Experts
  Jianan Nie, Peiyao Xiao, Kaiyi Ji, Peng Gao
  Preprint, 2026
  
• Agenra: A Language and Verified Core for Stateful LLM Agent Authorization
  Basavesh Ammanaghatta Shivakumar, Swarn Priya, Peng Gao
  arXiv:2608.22868, 2026
  [paper]
• Breaking Ambient Trust: In-Network Identity-Aware Microsegmentation Against Lateral Movement
  Osama Bajaber, Bo Ji, Peng Gao
  arXiv:2608.29979, 2026
  [paper]
• CTIFoundry: An Agent-Native Corpus Scaffold for Cyber Threat Intelligence
  Yutong Cheng, Changze Li, Qian Cui, Wei Ding, Lingzhi Wang, Yan Chen, Peng Gao
  arXiv:2608.18613, 2026
  [paper]
• BEACON: Behavior-Anchored Cross-Source Knowledge Graph Construction for Cyber Threat Intelligence
  Changze Li, Yutong Cheng, Tsania Camila Finnisa, Qian Cui, Wei Ding, Peng Gao
  arXiv:2608.28394, 2026
  [paper]
• CTI2TTP: Evidence-Grounded TTP Extraction from Cyber Threat Intelligence via Diverge-then-Converge Verification
  Yutong Cheng*, Changze Li* (* co-first authors), Raihan Sultan Pasha Basuki, Qian Cui, Wei Ding, Peng Gao
  arXiv:2605.25836, 2026
  [paper]

Refereed Conference, Workshop, and Journal Papers

• Benchmarking LLM Agents for SOC Alert Triage: Performance and Failure Modes
  Saimon Amanuel Tsegai, Peng Gao
  NeurIPS Workshop on Agents in the Wild: Safety, Security, and Beyond (NeurIPS AIWILD), December 2026
  
• AgentCap: Capability-Based Runtime Authorization for Secure LLM Agent Execution
  Aravinda Kashyap, Peng Gao
  NeurIPS Workshop on Agents in the Wild: Safety, Security, and Beyond (NeurIPS AIWILD), December 2026
  
• SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications
  Yutong Cheng, Haifeng Chen, Peng Gao, Wei Cheng
  Conference on Neural Information Processing Systems (NeurIPS), December 2026
  [paper]
  
• eMicro: Real-Time Multi-Hop Access Control for Microservices with eBPF
  Rizky Ramadhana Putra Kusnaryanto, Osama Bajaber, Saimon Amanuel Tsegai, Teryl Taylor, Frederico Araujo, Yuede Ji, Peng Gao
  ACM Conference on Computer and Communications Security (CCS), November 2026
  [paper] [code]
  
• CTIConnect: A Benchmark for Retrieval-Augmented LLMs over Heterogeneous Cyber Threat Intelligence
  Yutong Cheng, Yang Liu, Changze Li, Dawn Song, Peng Gao
  ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), August 2026
  [paper] [code and data]
  
• Escaping Whack-a-Mole: Optimizing Documentation as Repo-Specific Playbooks for Coding Agents
  Yutong Cheng, Haifeng Chen, Wenchao Yu, Xujiang Zhao, Peng Gao, Wei Cheng
  International Conference on Machine Learning (ICML), July 2026
  [paper]
• ReciNet: Reciprocal Space-Aware Long-Range Modeling for Crystalline Property Prediction
  Jianan Nie, Peiyao Xiao, Kaiyi Ji, Peng Gao
  Transactions on Machine Learning Research (TMLR), 2026
  [paper] [code]
  
• FlowMS: Flow Matching for De Novo Structure Elucidation from Mass Spectra
  Jianan Nie, Peng Gao
  ICLR Workshop on Foundation Models for Science (ICLR FM4Science), April 2026
  [paper]
  
• Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks
  Mahavir Dabas, Tran Huynh, Nikhil Reddy Billa, Jiachen T. Wang, Peng Gao, Charith Peris, Yao Ma, Rahul Gupta, Ming Jin, Prateek Mittal, Ruoxi Jia
  International Conference on Learning Representations (ICLR), April 2026
  [paper] [code]
  
• NL2Logic: AST-Guided Translation of Natural Language into First-Order Logic with Large Language Models
  Rizky Ramadhana Putra Kusnaryanto, Raihan Sultan Pasha Basuki, Yutong Cheng, Peng Gao
  Findings of the Association for Computational Linguistics: EACL (EACL Findings), March 2026
  [paper] [code]
  
• Off-the-Shelf Image-to-Image Models Are All You Need to Defeat Image Protection Schemes
  Xavier Pleimling, Sifat Muhammad Abdullah, Gunjan Balde, Peng Gao, Mainack Mondal, Murtuza Jadliwala, Bimal Viswanath
  IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), March 2026
  [paper] [code]
  
• NetCap: Data-Plane Capability-Based Defense Against Token Theft in Network Access
  Osama Bajaber, Bo Ji, Peng Gao
  Network and Distributed System Security Symposium (NDSS), February 2026
  [paper] [code]
  • U.S. patent application filed
  
• HuggingGraph: Understanding the Supply Chain of LLM Ecosystem
  Mohammad Shahedur Rahman, Peng Gao, Yuede Ji
  ACM International Conference on Information and Knowledge Management (CIKM), November 2025
  [paper] [data] [demo website]
  
• Enabling Efficient Attack Investigation via Human-in-the-Loop Security Analysis
  Saimon Amanuel Tsegai, Xinyu Yang, Haoyuan Liu, Peng Gao
  International Conference on Very Large Data Bases (VLDB), September 2025
  [paper] [code and demo video]
  
• CTINexus: Automatic Cyber Threat Intelligence Knowledge Graph Construction Using Large Language Models
  Yutong Cheng, Osama Bajaber, Saimon Amanuel Tsegai, Dawn Song, Peng Gao
  IEEE European Symposium on Security and Privacy (Euro S&P), June 2025
  [paper] [code and data]
  • Adopted by Palo Alto Networks, ThreatConnect, and other security companies for automated threat intelligence analysis
  • Tutorial presented at the NDSS 2026 PRISM workshop
• Madeline: Continuous and Low-cost Monitoring with Graph-free Representations to Combat Cyber Threats
  Wenjia Song, Hailun Ding, Na Meng, Peng Gao, Danfeng (Daphne) Yao
  Annual Computer Security Applications Conference (ACSAC), December 2024
  [paper]
  
• ThreatKG: An AI-Powered System for Automated Open-Source Cyber Threat Intelligence Gathering and Management
  Peng Gao*, Xiaoyuan Liu* (* co-first authors), Edward Choi, Sibo Ma, Xinyu Yang, Dawn Song
  ACM CCS Workshop on Large AI Systems and Models with Privacy and Safety Analysis (CCS LAMPS), October 2024
  [paper]
  • Influenced security products at Microsoft and Zscaler
• vFix: Facilitating Software Maintenance of Smart Contracts via Automatically Fixing Vulnerabilities
  Pengcheng Fang, Peng Gao, Yun Peng, Qingzhao Zhang, Tao Xie, Dawn Song, Prateek Mittal, Sanjeev R. Kulkarni, Zhuotao Liu, Xusheng Xiao
  IEEE International Conference on Software Maintenance and Evolution (ICSME), October 2024
  [paper] [code]
  
• P4Control: Line-Rate Cross-Host Attack Prevention via In-Network Information Flow Control Enabled by Programmable Switches and eBPF
  Osama Bajaber, Bo Ji, Peng Gao
  IEEE Symposium on Security and Privacy (S&P), May 2024
  [paper] [code] [talk]
  • U.S. patent application filed
  
• An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape
  Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi, Taejoong Chung, Peng Gao, Murtuza Jadliwala, Bimal Viswanath
  IEEE Symposium on Security and Privacy (S&P), May 2024
  [paper] [code and data] [talk]
  
• PrivMon: A Stream-Based System for Real-Time Privacy Attack Detection for Machine Learning Models
  Myeongseob Ko*, Xinyu Yang* (* co-first authors), Zhengjie Ji, Hoang Anh Just, Peng Gao, Anoop Kumar, Ruoxi Jia
  International Symposium on Research in Attacks, Intrusions and Defenses (RAID), October 2023
  [paper] [code]
  
• PrivGuard: Privacy Regulation Compliance Made Easier
  Lun Wang, Usmann Khan, Joseph P. Near, Qi Pang, Jithendaraa Subramanian, Neel Somani, Peng Gao, Andrew Low, Dawn Song
  USENIX Security Symposium (USENIX Security), August 2022
  [paper] [code]
  • Deployed in privacy products at Oasis Labs
  
• Back-Propagating System Dependency Impact for Attack Investigation
  Pengcheng Fang*, Peng Gao* (* co-first authors), Changlin Liu, Erman Ayday, Kangkook Jee, Ting Wang, Yanfang (Fanny) Ye, Zhuotao Liu, Xusheng Xiao
  USENIX Security Symposium (USENIX Security), August 2022
  [paper] [code]
• Make Web3.0 Connected
  Zhuotao Liu, Yangxi Xiang, Jian Shi, Peng Gao, Haoyu Wang, Xusheng Xiao, Bihan Wen, Qi Li, Yih-Chun Hu
  IEEE Transactions on Dependable and Secure Computing (TDSC), 2021
  [paper]
• CHAMP: Characterizing Undesired App Behaviors from User Comments based on Market Policies
  Yangyu Hu, Haoyu Wang, Tiantong Ji, Xusheng Xiao, Xiapu Luo, Peng Gao, Yao Guo
  IEEE/ACM International Conference on Software Engineering (ICSE), May 2021
  [paper] [code]
• Enabling Efficient Cyber Threat Hunting With Cyber Threat Intelligence
  Peng Gao, Fei Shao, Xiaoyuan Liu, Xusheng Xiao, Zheng Qin, Fengyuan Xu, Prateek Mittal, Sanjeev R. Kulkarni, Dawn Song
  IEEE International Conference on Data Engineering (ICDE), April 2021
  [paper] [demo video] [code]
  
• DeepIntent: Deep Icon-Behavior Learning for Detecting Intention-Behavior Discrepancy in Mobile Apps
  Shengqu Xi, Shao Yang, Xusheng Xiao, Yuan Yao, Yayuan Xiong, Fengyuan Xu, Haoyu Wang, Peng Gao, Zhuotao Liu, Feng Xu, Jian Lu
  ACM Conference on Computer and Communications Security (CCS), November 2019
  [paper] [code]
• HyperService: Interoperability and Programmability Across Heterogeneous Blockchains
  Zhuotao Liu, Yangxi Xiang, Jian Shi, Peng Gao, Haoyu Wang, Xusheng Xiao, Bihan Wen, Yih-Chun Hu
  ACM Conference on Computer and Communications Security (CCS), November 2019
  [paper] [long technical report] [code] [website]
• Data Capsule: A New Paradigm for Automatic Compliance with Data Privacy Regulations
  Lun Wang, Joseph P. Near, Neel Somani, Peng Gao, Andrew Low, David Dao, Dawn Song
  VLDB Workshop on Polystore Systems for Heterogeneous Data in Multiple Databases with Privacy and Security Assurances (VLDB POLY), August 2019
  [paper]
• IconIntent: Automatic Identification of Sensitive UI Widgets based on Icon Classification for Android Apps
  Xusheng Xiao, Xiaoyin Wang, Zhihao Cao, Hanlin Wang, Peng Gao
  IEEE/ACM International Conference on Software Engineering (ICSE), May 2019
  [paper]
• SAQL: A Stream-based Query System for Real-Time Abnormal System Behavior Detection
  Peng Gao, Xusheng Xiao, Ding Li, Zhichun Li, Kangkook Jee, Zhenyu Wu, Chung Hwan Kim, Sanjeev R. Kulkarni, Prateek Mittal
  USENIX Security Symposium (USENIX Security), August 2018
  [paper] [demo video]
  • 2018 CSAW Best Applied Security Paper Award Finalist
  • U.S. patent granted
  • Integrated into NEC Corporation's Automated Security Intelligence product, which won the 2016 CEATEC Innovation Award
  
• AIQL: Enabling Efficient Attack Investigation from System Monitoring Data
  Peng Gao, Xusheng Xiao, Zhichun Li, Kangkook Jee, Fengyuan Xu, Sanjeev R. Kulkarni, Prateek Mittal
  USENIX Annual Technical Conference (ATC), July 2018
  [paper] [demo video]
  • U.S. patent granted
  • Integrated into NEC Corporation's Automated Security Intelligence product, which won the 2016 CEATEC Innovation Award
  
• SybilFuse: Combining Local Attributes with Global Structure to Perform Robust Sybil Detection
  Peng Gao, Binghui Wang, Neil Zhenqiang Gong, Sanjeev R. Kulkarni, Kurt Thomas, Prateek Mittal
  IEEE Conference on Communications and Network Security (CNS), May 2018
  [paper]
  • Influenced fraud detection systems at Facebook
  
• Exploiting Temporal Dynamics in Sybil Defenses
  Changchang Liu*, Peng Gao* (* co-first authors), Matthew Wright, Prateek Mittal
  ACM Conference on Computer and Communications Security (CCS), October 2015
  [paper]

Refereed Demo Papers

• A Knowledge Base Question Answering System for Cyber Threat Knowledge Acquisition
  Zhengjie Ji, Edward Choi, Peng Gao
  IEEE International Conference on Data Engineering (ICDE Demo), Demonstrations Track, May 2022
  [paper]
  
• A System for Automated Open-Source Threat Intelligence Gathering and Management
  Peng Gao*, Xiaoyuan Liu* (* co-first authors), Edward Choi, Bhavna Soman, Chinmaya Mishra, Kate Farris, Dawn Song
  ACM SIGMOD International Conference on Management of Data (SIGMOD Demo), Demonstrations Track, June 2021
  [paper] [demo video] [data]
  • Featured in the Microsoft Security Response Center newsletter
• A System for Efficiently Hunting for Cyber Threats in Computer Systems Using Threat Intelligence
  Peng Gao, Fei Shao, Xiaoyuan Liu, Xusheng Xiao, Haoyuan Liu, Zheng Qin, Fengyuan Xu, Prateek Mittal, Sanjeev R. Kulkarni, Dawn Song
  IEEE International Conference on Data Engineering (ICDE Demo), Demonstrations Track, April 2021
  [paper]
  
• Querying Streaming System Monitoring Data for Enterprise System Anomaly Detection
  Peng Gao, Xusheng Xiao, Ding Li, Kangkook Jee, Haifeng Chen, Sanjeev R. Kulkarni, Prateek Mittal
  IEEE International Conference on Data Engineering (ICDE Demo), Demonstrations Track, April 2020
  [paper]
  
• A Query System for Efficiently Investigating Complex Attack Behaviors for Enterprise Security
  Peng Gao, Xusheng Xiao, Zhichun Li, Kangkook Jee, Fengyuan Xu, Sanjeev R. Kulkarni, Prateek Mittal
  International Conference on Very Large Data Bases (VLDB Demo), Demonstrations Track, August 2019
  [paper]