Alert button
Picture for Mantas Mazeika

Mantas Mazeika

Alert button

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Mar 06, 2024
Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatti, Justin D. Li, Ann-Kathrin Dombrowski, Shashwat Goel, Long Phan, Gabriel Mukobi, Nathan Helm-Burger, Rassin Lababidi, Lennart Justen, Andrew B. Liu, Michael Chen, Isabelle Barrass, Oliver Zhang, Xiaoyuan Zhu, Rishub Tamirisa, Bhrugu Bharathi, Adam Khoja, Zhenqi Zhao, Ariel Herbert-Voss, Cort B. Breuer, Andy Zou, Mantas Mazeika, Zifan Wang, Palash Oswal, Weiran Liu, Adam A. Hunt, Justin Tienken-Harder, Kevin Y. Shih, Kemper Talley, John Guan, Russell Kaplan, Ian Steneker, David Campbell, Brad Jokubaitis, Alex Levinson, Jean Wang, William Qian, Kallol Krishna Karmakar, Steven Basart, Stephen Fitz, Mindy Levine, Ponnurangam Kumaraguru, Uday Tupakula, Vijay Varadharajan, Yan Shoshitaishvili, Jimmy Ba, Kevin M. Esvelt, Alexandr Wang, Dan Hendrycks

Figure 1 for The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Figure 2 for The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Figure 3 for The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Figure 4 for The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Viaarxiv icon

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Feb 06, 2024
Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li, David Forsyth, Dan Hendrycks

Viaarxiv icon

Representation Engineering: A Top-Down Approach to AI Transparency

Oct 10, 2023
Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, Dan Hendrycks

Figure 1 for Representation Engineering: A Top-Down Approach to AI Transparency
Figure 2 for Representation Engineering: A Top-Down Approach to AI Transparency
Figure 3 for Representation Engineering: A Top-Down Approach to AI Transparency
Figure 4 for Representation Engineering: A Top-Down Approach to AI Transparency
Viaarxiv icon

An Overview of Catastrophic AI Risks

Jul 11, 2023
Dan Hendrycks, Mantas Mazeika, Thomas Woodside

Figure 1 for An Overview of Catastrophic AI Risks
Figure 2 for An Overview of Catastrophic AI Risks
Figure 3 for An Overview of Catastrophic AI Risks
Figure 4 for An Overview of Catastrophic AI Risks
Viaarxiv icon

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Jun 20, 2023
Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, Chenhui Zhang, Chejian Xu, Zidi Xiong, Ritik Dutta, Rylan Schaeffer, Sang T. Truong, Simran Arora, Mantas Mazeika, Dan Hendrycks, Zinan Lin, Yu Cheng, Sanmi Koyejo, Dawn Song, Bo Li

Figure 1 for DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Figure 2 for DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Figure 3 for DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Figure 4 for DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
Viaarxiv icon

How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios

Oct 18, 2022
Mantas Mazeika, Eric Tang, Andy Zou, Steven Basart, Jun Shern Chan, Dawn Song, David Forsyth, Jacob Steinhardt, Dan Hendrycks

Figure 1 for How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
Figure 2 for How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
Figure 3 for How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
Figure 4 for How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios
Viaarxiv icon

Forecasting Future World Events with Neural Networks

Jun 30, 2022
Andy Zou, Tristan Xiao, Ryan Jia, Joe Kwon, Mantas Mazeika, Richard Li, Dawn Song, Jacob Steinhardt, Owain Evans, Dan Hendrycks

Figure 1 for Forecasting Future World Events with Neural Networks
Figure 2 for Forecasting Future World Events with Neural Networks
Figure 3 for Forecasting Future World Events with Neural Networks
Figure 4 for Forecasting Future World Events with Neural Networks
Viaarxiv icon

How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection

Jun 28, 2022
Mantas Mazeika, Bo Li, David Forsyth

Figure 1 for How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
Figure 2 for How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
Figure 3 for How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
Figure 4 for How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
Viaarxiv icon