Alert button
Picture for Wenbo Guo

Wenbo Guo

Alert button

TextGuard: Provable Defense against Backdoor Attacks on Text Classification

Nov 25, 2023
Hengzhi Pei, Jinyuan Jia, Wenbo Guo, Bo Li, Dawn Song

Figure 1 for TextGuard: Provable Defense against Backdoor Attacks on Text Classification
Figure 2 for TextGuard: Provable Defense against Backdoor Attacks on Text Classification
Figure 3 for TextGuard: Provable Defense against Backdoor Attacks on Text Classification
Figure 4 for TextGuard: Provable Defense against Backdoor Attacks on Text Classification
Viaarxiv icon

netFound: Foundation Model for Network Security

Oct 25, 2023
Satyandra Guthula, Navya Battula, Roman Beltiukov, Wenbo Guo, Arpit Gupta

Figure 1 for netFound: Foundation Model for Network Security
Figure 2 for netFound: Foundation Model for Network Security
Figure 3 for netFound: Foundation Model for Network Security
Figure 4 for netFound: Foundation Model for Network Security
Viaarxiv icon

In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems

Jun 15, 2023
Roman Beltiukov, Wenbo Guo, Arpit Gupta, Walter Willinger

Figure 1 for In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems
Figure 2 for In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems
Figure 3 for In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems
Figure 4 for In Search of netUnicorn: A Data-Collection Platform to Develop Generalizable ML Models for Network Security Problems
Viaarxiv icon

Unique Identification of 50,000+ Virtual Reality Users from Head & Hand Motion Data

Feb 17, 2023
Vivek Nair, Wenbo Guo, Justus Mattern, Rui Wang, James F. O'Brien, Louis Rosenberg, Dawn Song

Figure 1 for Unique Identification of 50,000+ Virtual Reality Users from Head & Hand Motion Data
Figure 2 for Unique Identification of 50,000+ Virtual Reality Users from Head & Hand Motion Data
Figure 3 for Unique Identification of 50,000+ Virtual Reality Users from Head & Hand Motion Data
Figure 4 for Unique Identification of 50,000+ Virtual Reality Users from Head & Hand Motion Data
Viaarxiv icon

Are Shortest Rationales the Best Explanations for Human Understanding?

Mar 16, 2022
Hua Shen, Tongshuang Wu, Wenbo Guo, Ting-Hao 'Kenneth' Huang

Figure 1 for Are Shortest Rationales the Best Explanations for Human Understanding?
Figure 2 for Are Shortest Rationales the Best Explanations for Human Understanding?
Figure 3 for Are Shortest Rationales the Best Explanations for Human Understanding?
Figure 4 for Are Shortest Rationales the Best Explanations for Human Understanding?
Viaarxiv icon

BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning

May 07, 2021
Lun Wang, Zaynah Javed, Xian Wu, Wenbo Guo, Xinyu Xing, Dawn Song

Figure 1 for BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Figure 2 for BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Figure 3 for BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Figure 4 for BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning
Viaarxiv icon

Robust saliency maps with decoy-enhanced saliency score

Feb 03, 2020
Yang Lu, Wenbo Guo, Xinyu Xing, William Stafford Noble

Figure 1 for Robust saliency maps with decoy-enhanced saliency score
Figure 2 for Robust saliency maps with decoy-enhanced saliency score
Figure 3 for Robust saliency maps with decoy-enhanced saliency score
Figure 4 for Robust saliency maps with decoy-enhanced saliency score
Viaarxiv icon

TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems

Aug 08, 2019
Wenbo Guo, Lun Wang, Xinyu Xing, Min Du, Dawn Song

Figure 1 for TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Figure 2 for TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Figure 3 for TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Figure 4 for TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
Viaarxiv icon