How NOT to Train Your Hack Bot: Dos and Don'ts of Building Offensive GPTs

Автор: Black Hat

Загружено: 2024-02-06

Просмотров: 5236

Описание: No doubt everybody is curious if you can use large language models (LLMs) for offensive security operations.

In this talk, we will demonstrate how you can and can't use LLMs like GPT4 to find security vulnerabilities in applications, and discuss in detail the promise and limitations of using LLMs this way.

We will go deep on how LLMs work and share state-of-the-art techniques for using them in offensive contexts.

By: Shane Caldwell , Ariel Herbert-Voss

Full Abstract and Presentation Materials: https://www.blackhat.com/us-23/briefi...

Не удается загрузить Youtube-плеер. Проверьте блокировку Youtube в вашей сети.
Повторяем попытку...

How NOT to Train Your Hack Bot: Dos and Don'ts of Building Offensive GPTs

Доступные форматы для скачивания:

Скачать видео

Информация по загрузке:

Скачать аудио

Похожие видео

Как я нашел своего первого жука (теперь и вы сможете)

Как я нашел своего первого жука (теперь и вы сможете)

Lifting the Fog of War - Monitoring, Identifying and Mitigating MS-RPC Based Threats

Lifting the Fog of War - Monitoring, Identifying and Mitigating MS-RPC Based Threats

Something Rotten in the State of Data Centers

Something Rotten in the State of Data Centers

Practical LLM Security: Takeaways From a Year in the Trenches

Practical LLM Security: Takeaways From a Year in the Trenches

What are AI Agents?

What are AI Agents?

Chasing Your Tail With a Raspberry Pi

Chasing Your Tail With a Raspberry Pi

Германия только что создала машину, которая могла бы бесконечно обеспечивать энергией всю планету.

Германия только что создала машину, которая могла бы бесконечно обеспечивать энергией всю планету.

5 лучших хакерских инструментов от бывшего хакера Black Hat

5 лучших хакерских инструментов от бывшего хакера Black Hat

Compromising LLMs: The Advent of AI Malware

Compromising LLMs: The Advent of AI Malware

A Decade After Stuxnet: How Siemens S7 is Still an Attacker's Heaven

A Decade After Stuxnet: How Siemens S7 is Still an Attacker's Heaven

🔥 Run HACKING LLM / AIs locally – RIGHT NOW! 🚀

🔥 Run HACKING LLM / AIs locally – RIGHT NOW! 🚀

DEF CON 31 - Contactless Overflow Code Execution in Payment Terminals & ATMs - Josep Rodriguez

DEF CON 31 - Contactless Overflow Code Execution in Payment Terminals & ATMs - Josep Rodriguez

Forward Focus: Perspectives on AI, Hype, and Security

Forward Focus: Perspectives on AI, Hype, and Security

LLM Security & Observability

LLM Security & Observability

How to Train LLMs to

How to Train LLMs to "Think" (o1 & DeepSeek-R1)

API Hacking Toolbox w/ Dr. Katie Paxton-Fear

API Hacking Toolbox w/ Dr. Katie Paxton-Fear

Hacking LLMs Demo and Tutorial (Explore AI Security Vulnerabilities)

Hacking LLMs Demo and Tutorial (Explore AI Security Vulnerabilities)

How Hackers Attack AI Models (and How to Stop Them)

How Hackers Attack AI Models (and How to Stop Them)

IAM The One Who Knocks

IAM The One Who Knocks

Intro to LLM Security - OWASP Top 10 for Large Language Models (LLMs)

Intro to LLM Security - OWASP Top 10 for Large Language Models (LLMs)