paper-with-me

홈 › Papers

Lessons From Red Teaming 100 Generative AI Products

2025-01-13 · Blake Bullwinkel, Amanda Minnich, Shiven Chawla, Gary Lopez, Martin Pouliot, Whitney Maxwell, Joris de Gruyter, Katherine Pratt, Saphir Qi, Nina Chikanov, Roman Lutz, Raja Sekhar Rao Dheekonda, Bolor-Erdene Jagdagdorj, Eugenia Kim, Justin Song, Keegan Hines, Daniel Jones, Giorgio Severi, Richard Lundeen, Sam Vaughan, Victoria Westerhoff, Pete Bryan, Ram Shankar Siva Kumar, Yonatan Zunger, Chang Kawaguchi, Mark Russinovich

In recent years, AI red teaming has emerged as a practice for probing the safety and security of generative AI systems. Due to the nascency of the field, there are many open questions about how red teaming operations should be conducted. Based on our experience red teaming over 100 generative AI products at Microsoft, we present our internal threat model ontology and eight main lessons we have learned: 1. Understand what the system can do and where it is applied 2. You don't have to compute gradients to break an AI system 3. AI red teaming is not safety benchmarking 4. Automation can help cover more of the risk landscape 5. The human element of AI red teaming is crucial 6. Responsible AI harms are pervasive but difficult to measure 7. LLMs amplify existing security risks and introduce new ones 8. The work of securing AI systems will never be complete By sharing these insights alongside case studies from our operations, we offer practical recommendations aimed at aligning red teaming efforts with real world risks. We also highlight aspects of AI red teaming that we believe are often misunderstood and discuss open questions for the field to consider.

📄 PDF Abstract BibTeX arXiv:2501.07238

Code (0)

등록된 구현이 없습니다.

Tasks

BenchmarkingRed Teaming

Methods 이 논문이 사용한 방법론

Ontology 설명 없음

Similar Papers 제목 키워드 기반

AI red-teaming is a sociotechnical challenge: on values, labor, and harms

2024-12-12 · Tarleton Gillespie, Ryland Shaw, Mary L. Gray, Jina Suh

As generative AI technologies find more and more real-world applications, the importance of testing their performance and safety seems paramount. "Red-teaming" has quickly become the primary approach to test AI models--p…

Red Teaming

Towards Red Teaming in Multimodal and Multilingual Translation

2024-01-29 · Christophe Ropers, David Dale, Prangthip Hansanti, Gabriel Mejia Gonzalez 외

Assessing performance in Natural Language Processing is becoming increasingly complex. One particular challenge is the potential for evaluation datasets to overlap with training data, either directly or indirectly, which…

Machine TranslationRed TeamingTranslation

Enabling Intuitive Human-Robot Teaming Using Augmented Reality and Gesture Control

2019-09-13 · Jason M. Gregory, Christopher Reardon, Kevin Lee, Geoffrey White 외

Human-robot teaming offers great potential because of the opportunities to combine strengths of heterogeneous agents. However, one of the critical challenges in realizing an effective human-robot team is efficient inform…

PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI

2026-05-07 · Wesley Hanwen Deng, Mingxi Yan, Sunnie S. Y. Kim, Akshita Jha 외 arxiv

Recent developments in AI safety research have called for red-teaming methods that effectively surface potential risks posed by generative AI models, with growing emphasis on how red-teamers' backgrounds and perspectives…

Exploring Large Language Models to Facilitate Variable Autonomy for Human-Robot Teaming

2023-12-12 · Younes Lakhnati, Max Pascher, Jens Gerken

In a rapidly evolving digital landscape autonomous tools and robots are becoming commonplace. Recognizing the significance of this development, this paper explores the integration of Large Language Models (LLMs) like Gen…

Unity