Artwork

Kandungan disediakan oleh N2K Networks Inc. and N2K Networks. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh N2K Networks Inc. and N2K Networks atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.
Player FM - Aplikasi Podcast
Pergi ke luar talian dengan aplikasi Player FM !

Prompts gone rogue.

25:44
 
Kongsi
 

Manage episode 433401781 series 2881647
Kandungan disediakan oleh N2K Networks Inc. and N2K Networks. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh N2K Networks Inc. and N2K Networks atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.

Shachar Menashe, Senior Director of Security Research at JFrog, is talking about "When Prompts Go Rogue: Analyzing a Prompt Injection Code Execution in Vanna.AI." A security vulnerability in the Vanna.AI tool, called CVE-2024-5565, allows hackers to exploit large language models (LLMs) by manipulating user input to execute malicious code, a method known as prompt injection.

This poses a significant risk when LLMs are connected to critical functions, highlighting the need for stronger security measures.

The research can be found here:

Learn more about your ad choices. Visit megaphone.fm/adchoices

  continue reading

361 episod

Artwork

Prompts gone rogue.

Research Saturday

26 subscribers

published

iconKongsi
 
Manage episode 433401781 series 2881647
Kandungan disediakan oleh N2K Networks Inc. and N2K Networks. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh N2K Networks Inc. and N2K Networks atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.

Shachar Menashe, Senior Director of Security Research at JFrog, is talking about "When Prompts Go Rogue: Analyzing a Prompt Injection Code Execution in Vanna.AI." A security vulnerability in the Vanna.AI tool, called CVE-2024-5565, allows hackers to exploit large language models (LLMs) by manipulating user input to execute malicious code, a method known as prompt injection.

This poses a significant risk when LLMs are connected to critical functions, highlighting the need for stronger security measures.

The research can be found here:

Learn more about your ad choices. Visit megaphone.fm/adchoices

  continue reading

361 episod

Semua episod

×
 
Loading …

Selamat datang ke Player FM

Player FM mengimbas laman-laman web bagi podcast berkualiti tinggi untuk anda nikmati sekarang. Ia merupakan aplikasi podcast terbaik dan berfungsi untuk Android, iPhone, dan web. Daftar untuk melaraskan langganan merentasi peranti.

 

Panduan Rujukan Pantas

Podcast Teratas