Wenbo Guo Department of Computer Science University of California, Santa Barbara E-mail: henrygwb@ucsb.edu Office: Harold Frank Hall, Santa Barbara, CA 93106 Github   Twitter

I am actively recruiting Ph.D. students. If you have a solid background in foundation models, DRL, or software security skills (program analysis, fuzzing, reverse engineering) and are interested in working with me, please do not hesitate to contact me through email.

• IBM Fellowship Award, IBM, 2020.
• Facebook Fellowship Finalist, Facebook, 2020.
• Baidu AI Fellowship Finalist, Baidu, 2020.
• Excellent Teaching Support Award, IST, Penn State, 2020.
• Excellent Research Award, IST, Penn State, 2019.
• Black Hat Student Scholarship, Black Hat, 2018-2020.
• Multiple Conference Travel Grants (e.g., USENIX Security, CCS, NeurIPS, ICML), 2018-2021.
• CCS Outstanding Paper Award, ACM, 2018.
• Outstanding Graduate student, SJTU, 2017.

2024

• TextGuard: Provable Defense against Backdoor Attacks on Text Classification
  Hengzhi Pei, Jinyuan Jia, Wenbo Guo, Bo Li, Dawn Song
  Proceedings of The 31st Conference on Network and Distributed System Security Symposium (NDSS)
  San Diego, CA, February 2024

2023

• BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning
  Xuan Chen, Wenbo Guo, Guanhong Tao, Xiangyu Zhang, Dawn Song
  Proceedings of The 37th Conference on Neural Information Processing Systems (NeurIPS)
  New Orleans, LA, December, 2023

• StateMask: Explaining Deep Reinforcement Learning through State Mask
  Zelei Cheng, Xian Wu, Jiahao Yu, Wenhai Sun, Wenbo Guo, Xinyu Xing
  Proceedings of The 37th Conference on Neural Information Processing Systems (NeurIPS)
  New Orleans, LA, December, 2023

• RAVE: Enabling safety verification for realistic deep reinforcement learning systems
  Wenbo Guo, Taesung Lee, Kevin Eykholt, Jiyong Jang
  Proceedings of Multi-Agent Security Workshop at NeurIPS
  New Orleans, LA, December, 2023

• In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems [code]
  Roman Beltiukov, Wenbo Guo, Arpit Gupta, Walter Willinger
  Proceedings of The 30th ACM Conference on Computer and Communications Security (CCS)
  Copenhagen, Denmark, November 2023

• 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
  Proceedings of The 32nd USENIX Security Symposium (USENIX Security)
  Anaheim, CA, August 2023

• PATROL: Provable Defense against Adversarial Policy in Two-player Games [code]
  Wenbo Guo, Xian Wu, Lun Wang, Xinyu Xing, Dawn Song
  Proceedings of The 32nd USENIX Security Symposium (USENIX Security)
  Anaheim, CA, August 2023

• AIRS: Explanation for Deep Reinforcement Learning based Security Applications
  Jiahao Yu, Wenbo Guo, Qi Qin, Gang Wang, Ting Wang, Xinyu Xing
  Proceedings of The 32nd USENIX Security Symposium (USENIX Security)
  Anaheim, CA, August 2023

• From Grim Reality to Practical Solution: Malware Classification in Real-World Noise
  Xian Wu, Wenbo Guo, Jia Yan, Baris Coskun, Xinyu Xing
  Proceedings of The 44th IEEE Symposium on Security and Privacy (S&P)
  San Francisco, CA, May 2023

2022

• Are Shortest Rationales the Best Explanations For Human Understanding? [code]
  Hua Shen, Tongshuang Wu, Wenbo Guo, Ting-Hao (Kenneth) Huang
  Proceedings of The 60th Annual Meeting of the Association for Computational Linguistics (ACL)
  Dublin, Ireland, May 2022 (Acceptance rate: 779/3088=25.22%)

2021

• EDGE: Explaining Deep Reinforcement Learning Policies [code]
  Wenbo Guo, Xian Wu, Usmann Khan, Xinyu Xing
  Proceedings of The 35th Annual Conference on Neural Information Processing Systems (NeurIPS)
  Virtual Conference, December 2021 (Acceptance rate: 2372/9122=26.00%)
• Adversarial Policy Learning in Two-player Competitive Games [code]
  Wenbo Guo, Xian Wu, Sui Huang, Xinyu Xing
  Proceedings of The 38th International Conference on Machine Learning (ICML)
  Virtual Conference, July 2021 (Acceptance rate: 1184/5513=21.48%)
• DANCE: Enhancing saliency maps using decoys [code]
  Yang Lu**, Wenbo Guo**, Xinyu Xing, William Stafford Noble
  Proceedings of The 38th International Conference on Machine Learning (ICML)
  Virtual Conference, July 2021 (Acceptance rate: 1184/5513=21.48%)
• RNNRepair: Automatic RNN Repair via Model-based Analysis [code]
  Xiaofei Xie, Wenbo Guo, Lei Ma, Wei Le, Jian Wang, Lingjun Zhou, Xinyu Xing, Yang Liu
  Proceedings of The 38th International Conference on Machine Learning (ICML)
  Virtual Conference, July 2021 (Acceptance rate: 1184/5513=21.48%)
• Adversarial Policy Training against Deep Reinforcement Learning [code]
  Wenbo Guo**, Xian Wu**, Hua Wei**, Xinyu Xing
  Proceedings of The 30th USENIX Security Symposium (USENIX Security)
  Virtual Conference, August 2021 (Acceptance rate 248/1319=18.80%) (Artifact Evaluated)
• CADE: Detecting and Explaining Concept Drift Samples for Security Applications [code]
  Limin Yang, Wenbo Guo, Qingying Hao, Arridhana Ciptadi, Ali Ahmadzadeh, Xinyu Xing, Gang Wang
  Proceedings of The 30th USENIX Security Symposium (USENIX Security)
  Virtual Conference, Canada, August 2021 (Acceptance rate 248/1319=18.80%) (Artifact Evaluated)
• BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
  Lun Wang, Zaynah Javed, Xian Wu, Wenbo Guo, Xinyu Xing, Dawn Song
  Proceedings of The 30th International Joint Conference on Artificial Intelligence (IJCAI)
  Virtual Conference, August 2021 (Acceptance rate: 587/4204=13.96%)
• FARE: Enabling Fine-grained Attack Categorization under Low-quality Labeled Data [code]
  Junjie Liang**, Wenbo Guo**, Tongbo Luo, Vasant Honavar, Gang Wang, Xinyu Xing
  Proceedings of The 28th Network and Distributed System Security Symposium (NDSS)
  Virtual Conference, February 2021 (Acceptance rate: 15.2%)
• 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
  Proceedings of The 20th IEEE International Conference on Data Mining (ICDM)
  Sorrento, Italy, November 2020 (Acceptance rate: 91/930=9.78%)
• Ruling StarCraft Game Spitefully -- Exploiting the Blind Spot of AI-Powered Game Bots
  Wenbo Guo, Xian Wu, Xinyu Xing, Jimmy Su
  Proceedings of The 23rd Blackhat USA (BlackHat USA)
  Las Vegas, NV, August 2020 (Press release: EurekAlert, Penn State News)
  

2019

• RENN: Efficient Reverse Execution with Neural-network-assisted Alias Analysis [code]
  Dongliang Mu**, Wenbo Guo**, Alejandro Cuevas, Yueqi Chen, Jinxuan Gai, Xinyu Xing, Bing Mao, Chengyu Song
  Proceedings of The 34th IEEE/ACM International Conference on Automated Software Engineering (ASE)
  San Diego, CA, November 2019 (Acceptance rate: 93/445=20.89%)
• DEEPVSA: Facilitating Value-set Analysis with Deep Learning for Postmortem Program Analysis [code]
  Wenbo Guo**, Dongliang Mu**, Xinyu Xing, Min Du, Dawn Song
  Proceedings of The 28th USENIX Security Symposium (USENIX Security)
  Santa Clara, CA, August 2019 (Acceptance rate: 113/719=15.72%)
• Towards the Detection of Inconsistencies in Public Security Vulnerability Reports [code]
  Ying Dong, Wenbo Guo, Yueqi Chen, Xinyu Xing, Yuqing Zhang, Gang Wang
  Proceedings of The 28th USENIX Security Symposium (USENIX Security)
  Santa Clara, CA, August 2019 (Acceptance rate: 113/719=15.72%)

2018

• Explaining Deep Learning Models -- A Bayesian Non-parametric Approach [code]
  Wenbo Guo, Sui Huang, Yunzhe Tao, Xinyu Xing, Lin Lin
  Proceedings of The 32nd Annual Conference on Neural Information Processing Systems (NeurIPS)
  Montreal, Canada, December 2018 (Acceptance rate: 1011/4856=20.82%)
• LEMNA: Explaining Deep Learning based Security Applications [slides] [code]
  Wenbo Guo, Dongliang Mu, Jun Xu, Purui Su, Gang Wang, Xinyu Xing
  Proceedings of The 25th ACM Conference on Computer and Communications Security (CCS)
  Toronto, Canada, October 2018 (Outstanding paper award: 2/809=0.25%) (Press release: Penn State News)
• 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.
  Proceedings of The 20th IEEE International Conference on Data Mining (ICDM)
  Singapore, November 2018 (Oral presentation: 84/948=8.86%)
• Active Learning Support Vector Machines with Low-Rank Transformation
  Liang Gong, Wenbo Guo*, Yupu Yang.
  Intelligent Data Analysis, 22.4 (2018): 701-715.

2017

• 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
  Proceedings of The 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
  Halifax, Nova Scotia, August 2017 (Acceptance rate: 131/748=17.51%)

(**equal contribution, *corresponding author)

• CS 529: Security Analytics
  Instructor, Purdue, Fall 2023
• CYBER 366: Malware Analytics
  Instructor/Teaching Assistant, Penn State, Fall 2019
  Awarded the Excellent Teaching Award
• Neural Network, Fuzzy Control and Expert System
  Teaching Assistant, SJTU, Spring 2015
  

• Geekpwn Competition on Data Tracing CTF.
  Top 10, August, 2018.
  
• Geekpwn Competition on Advesarial Attacks and Defenses CTF.
  Finalist (Top 6 worldwide), August, 2018. (Press release: Penn State News, CCTV, CSDN, TOM)
  
• Kanxue AI CTF.
  Competition Question Maker, June, 2018. (Press release: China Daily, kknews)
  

• Program Committee Member:
• USENIX Security'24
• CCS'23, CCS'22, CCS'21
• S&P'23 (Poster PC), S&P'22 (Poster PC), S&P'21 (Shadow PC)
• ICLR'24, ICLR'23, ICLR'22
• ICML'23, ICML'22, ICML'21
• NeurIPS'23, NeurIPS'22, NeurIPS'21
• MLsys'23 (Workflow Chair)
• AAAI'23, AAAI'22, AAAI'21
• RAID'22
• XAI4DEBUGGING'21
• MLHAT'21
• WAD'21
• DEEPVISON'20
• SPAI'20