(**equal contribution)

Preprint

• RL-JACK: Reinforcement Learning-powered Black-box Jailbreaking Attack against LLMs
  Xuan Chen, Yuzhou Nie, Lu Yan, Yunshu Mao, Wenbo Guo, Xiangyu Zhang
  LLM safety/red-teaming
• TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models
  Yuzhou Nie, Yanting Wang, Jinyuan Jia, Michael De Lucia, Nathaniel Bastian, Wenbo Guo, Dawn Song
  LLM safety/red-teaming
• BandFuzz: A Practical Framework for Collaborative Fuzzing with Reinforcement Learning
  Wenxuan Shi, Hongwei Li, Jiahao Yu, Wenbo Guo, Xinyu Xing
  DRL for software security

2024

• When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
  Xuan Chen, Yuzhou Nie, Wenbo Guo, Xiangyu Zhang
  In Annual Conference on Neural Information Processing Systems (NeurIPS)
  LLM safety/red-teaming
• DFBA: Data Free Backdoor Attacks
  Bochuan Cao, Jinyuan Jia, Chuxuan Hu, Wenbo Guo, Zhen Xiang, Jinghui Chen, Bo Li, Dawn Song
  In Annual Conference on Neural Information Processing Systems (NeurIPS)
  ML safety
• FORAY: Towards Effective Attack Synthesis against Deep Logical Vulnerabilities in DeFi Protocols
  Hongbo Wen, Hanzhi Liu, Jiaxin Song, Yanju Chen, Wenbo Guo, Yu Feng
  In ACM Conference on Computer and Communications Security (CCS)
  
• GuideEnricher: Protecting the Anonymity of Ethereum Mixing Service Users with Deep Reinforcement Learning
  Ravindu De Silva, Wenbo Guo, Nicola Ruaro, Ilya Grishchenko, Christopher Kruegel, Giovanni Vigna
  In USENIX Security Symposium (USENIX Security)
  DRL for Web3 security Code
• SHINE: Shielding Backdoors in Deep Reinforcement Learning
  Zhuowen Yuan, Wenbo Guo, Jinyuan Jia, Bo Li, Dawn Song
  In International Conference on Machine Learning (ICML)
  DRL robustness Code
• BOXRR-23: 4.7 Million Motion Capture Recordings from 105,000 VR Users
  Vivek Nair, Wenbo Guo, Rui Wang, James F. O'Brien, Louis Rosenberg, Dawn Song
  In IEEE Conference on Virtual Reality and 3D User Interfaces (VR)
  ML for VR/AR security Dataset
• TextGuard: Provable Defense against Backdoor Attacks on Text Classification
  Hengzhi Pei, Jinyuan Jia, Wenbo Guo, Bo Li, Dawn Song
  In The Conference on Network and Distributed System Security Symposium (NDSS)
  Foundation model (LLM) security Code

2023

• BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning
  Xuan Chen, Wenbo Guo, Guanhong Tao, Xiangyu Zhang, Dawn Song
  In Annual Conference on Neural Information Processing Systems (NeurIPS)
  DRL robustness Code
• StateMask: Explaining Deep Reinforcement Learning through State Mask
  Zelei Cheng, Xian Wu, Jiahao Yu, Wenhai Sun, Wenbo Guo, Xinyu Xing
  In Annual Conference on Neural Information Processing Systems (NeurIPS)
  DRL interpretability Code
• RAVE: Enabling safety verification for realistic deep reinforcement learning systems
  Wenbo Guo, Taesung Lee, Kevin Eykholt, Jiyong Jang
  In Multi-Agent Security Workshop at NeurIPS
  DRL robustness
• In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems
  Roman Beltiukov, Wenbo Guo, Arpit Gupta, Walter Willinger
  In ACM Conference on Computer and Communications Security (CCS)
  ML for network security Code
• Unique Identification of 50,000+ Virtual Reality Users from Head & Hand Motion Data
  Vivek Nair, Wenbo Guo, Justus Mattern, Rui Wang, James F. O'Brien, Louis Rosenberg, Dawn Song
  In USENIX Security Symposium (USENIX Security)
  ML for AR/VR security Code (Press release: Fox, Bloomberg)
• PATROL: Provable Defense against Adversarial Policy in Two-player Games
  Wenbo Guo, Xian Wu, Lun Wang, Xinyu Xing, Dawn Song
  In USENIX Security Symposium (USENIX Security)
  RL robustness Code
• AIRS: Explanation for Deep Reinforcement Learning based Security Applications
  Jiahao Yu, Wenbo Guo, Qi Qin, Gang Wang, Ting Wang, Xinyu Xing
  In USENIX Security Symposium (USENIX Security)
  RL interpretability Code
• From Grim Reality to Practical Solution: Malware Classification in Real-World Noise
  Xian Wu, Wenbo Guo, Jia Yan, Baris Coskun, Xinyu Xing
  In IEEE Symposium on Security and Privacy (S&P)
  ML for software security Code

2022

• Are Shortest Rationales the Best Explanations For Human Understanding?
  Hua Shen, Tongshuang Wu, Wenbo Guo, Ting-Hao (Kenneth) Huang
  In The Annual Meeting of the Association for Computational Linguistics (ACL)
  DL interpretability Code

2021

• EDGE: Explaining Deep Reinforcement Learning Policies
  Wenbo Guo, Xian Wu, Usmann Khan, Xinyu Xing
  In Annual Conference on Neural Information Processing Systems (NeurIPS)
  DRL interpretability Code
• Adversarial Policy Learning in Two-player Competitive Games
  Wenbo Guo, Xian Wu, Sui Huang, Xinyu Xing
  In The International Conference on Machine Learning (ICML)
  DRL robustness Code
• DANCE: Enhancing saliency maps using decoys
  Yang Lu**, Wenbo Guo**, Xinyu Xing, William Stafford Noble
  In The International Conference on Machine Learning (ICML)
  DL interpretability Code
• RNNRepair: Automatic RNN Repair via Model-based Analysis
  Xiaofei Xie, Wenbo Guo, Lei Ma, Wei Le, Jian Wang, Lingjun Zhou, Xinyu Xing, Yang Liu
  In The International Conference on Machine Learning (ICML)
  DL robustness Code
• Adversarial Policy Training against Deep Reinforcement Learning
  Wenbo Guo**, Xian Wu**, Hua Wei**, Xinyu Xing
  In USENIX Security Symposium (USENIX Security)
  DRL robustness Code
• CADE: Detecting and Explaining Concept Drift Samples for Security Applications
  Limin Yang, Wenbo Guo, Qingying Hao, Arridhana Ciptadi, Ali Ahmadzadeh, Xinyu Xing, Gang Wang
  In USENIX Security Symposium (USENIX Security)
  ML for software/network security Code
• BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
  Lun Wang, Zaynah Javed, Xian Wu, Wenbo Guo, Xinyu Xing, Dawn Song
  In International Joint Conference on Artificial Intelligence (IJCAI)
  DRL robustness
• FARE: Enabling Fine-grained Attack Categorization under Low-quality Labeled Data
  Junjie Liang**, Wenbo Guo**, Tongbo Luo, Vasant Honavar, Gang Wang, Xinyu Xing
  In The Network and Distributed System Security Symposium (NDSS)
  ML for software/network security Code
• Data-driven analysis of the electronic-structure factors controlling the work functions of perovskites oxides
  Yihuang Xiong, Weinan Chen, Wenbo Guo, Hua Wei, Ismaila Dabo
  Physical Chemistry Chemical Physics

2020

• Towards Inspecting and Eliminating Trojan Backdoors in Deep Neural Networks
  Wenbo Guo**, Lun Wang**, Yan Xu, Xinyu Xing, Min Du, Dawn Song
  In IEEE International Conference on Data Mining (ICDM)
  DL robustness
• Ruling StarCraft Game Spitefully -- Exploiting the Blind Spot of AI-Powered Game Bots
  Wenbo Guo, Xian Wu, Xinyu Xing, Jimmy Su
  In The Blackhat USA (BlackHat USA)
  DRL robustness (Press release: EurekAlert, Penn State News)
  

2019

• RENN: Efficient Reverse Execution with Neural-network-assisted Alias Analysis
  Dongliang Mu**, Wenbo Guo**, Alejandro Cuevas, Yueqi Chen, Jinxuan Gai, Xinyu Xing, Bing Mao, Chengyu Song
  In IEEE/ACM International Conference on Automated Software Engineering (ASE)
  ML for software security Code
• DEEPVSA: Facilitating Value-set Analysis with Deep Learning for Postmortem Program Analysis
  Wenbo Guo**, Dongliang Mu**, Xinyu Xing, Min Du, Dawn Song
  In USENIX Security Symposium (USENIX Security)
  ML for software security Code
• Towards the Detection of Inconsistencies in Public Security Vulnerability Reports
  Ying Dong, Wenbo Guo, Yueqi Chen, Xinyu Xing, Yuqing Zhang, Gang Wang
  In USENIX Security Symposium (USENIX Security)
  ML for software security Code

2017-2018

• Explaining Deep Learning Models -- A Bayesian Non-parametric Approach
  Wenbo Guo, Sui Huang, Yunzhe Tao, Xinyu Xing, Lin Lin
  In Annual Conference on Neural Information Processing Systems (NeurIPS)
  DL interpretability Code
• LEMNA: Explaining Deep Learning based Security Applications
  Wenbo Guo, Dongliang Mu, Jun Xu, Purui Su, Gang Wang, Xinyu Xing
  In ACM Conference on Computer and Communications Security (CCS)
  DL interpretability DL for software security Code Slides Outstanding paper award
• Defending against Adversarial Samples without Security through Obscurity
  Wenbo Guo, Qinglong Wang, Kaixuan Zhang, Alexander G. Ororbia II, Sui Huang, Xue Liu, C. Lee Giles, Lin Lin, Xinyu Xing.
  In IEEE International Conference on Data Mining (ICDM)
  DL Robustness
• Adversary Resistant Deep Neural Networks with an Application to Malware Detection
  Wenbo Guo**, Qinglong Wang**, Kaixuan Zhang, Alexander G. Ororbia II, Xinyu Xing, Xue Liu, C. Lee Giles
  In ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
  DL Robustness