by Natalie Pistunovich & Ivan Kwiatkowski
Welcome to the SAI podcast, where intellectual curiosity and technical expertise meet. Natalie is an OpenAI Developer Ambassador and Ivan is a Senior Security Researcher at Kaspersky. Together we ask questions and learn, each one bringing their expertise. We're covering the different cross sections: how can AI be used in cybersecurity, how can AI be more secure, what attacks can be done, how to prepare, etc. All the topics are introduced at a high level and occasionally we dive deeper in.
Language
🇺🇲
Publishing Since
5/3/2023
Pitch yourself as a guest, propose sponsorships, or reach out directly to the host.
October 1, 2023
<p>In this episode, Natalie and Ivan, in a conference call with members of GenAI, discuss OpenAI's cybersecurity grant program, and go over the suggestions made to applicants by the company on its webpage.</p>
July 21, 2023
<p>In this episode, we go through OWASP's recently released <a href="https://owasp.org/www-project-top-10-for-large-language-model-applications/descriptions/" target="_blank" rel="noopener noreferer">list of vulnerability classes for LLMs</a>. The list includes:</p> <ul> <li>Prompt injections</li> <li>Data leakage</li> <li>Inadequate sandboxing</li> <li>Unauthorized code execution</li> <li>SSRF vulnerabilities</li> <li>Overreliance on LLM-generated content</li> <li>Inadequate AI alignment</li> <li>Insufficient access controls</li> <li>Improper error handling</li> <li>Training data poisoning</li> </ul> <p>We note that while some of the items on this list are definitely worth mentioning, others feel a bit more disconnected from the topic of cybersecurity and likely can't be solved through technical means.</p> <p><br></p> <p>Reference: Rich Harang's <a href="https://twitter.com/rharang/status/1661473877623713793" target="_blank" rel="noopener noreferer">twitter thread on the subject</a>.</p>
June 22, 2023
<p>This episode focuses on whether social engineering techniques, traditionally used against humans, could be leveraged against language models.</p> <p>Natalie and Ivan start by discussing the use of LLMs in capture the flag competitions, and mention the emergence of new types of challenges revolving around <a href="https://www.aicrowd.com/challenges/hackaprompt-2023" target="_blank" rel="noopener noreferer">prompt hacking</a>. This leads the discussion towards the <a href="https://www.jailbreakchat.com/" target="_blank" rel="noopener noreferer">various ways</a> that can be used to circumvent a model's fine tuning. The hosts discuss the challenges and scoring systems in such competitions, as well as the potential ethical concerns in exploring the capabilities and limitations of AI language models. </p> <p>They draw parallels between AI prompt crafting and social engineering, speculating on how techniques used in human social engineering could potentially be adapted for AI prompt hacking. Overall, the conversation explores the evolving relationship between security, AI, and the ethical considerations surrounding the use of language models in hacking competitions.</p>
Have a different question and can't find the answer you're looking for? Reach out to our support team by sending us an email and we'll get back to you as soon as we can.
Welcome to the SAI podcast, where intellectual curiosity and technical expertise meet.
Natalie is an OpenAI Developer Ambassador and Ivan is a Senior Security Researcher at Kaspersky.
Together we ask questions and learn, each one bringing their expertise. We're covering the different cross sections: how can AI be used in cybersecurity, how can AI be more secure, what attacks can be done, how to prepare, etc.
All the topics are introduced at a high level and occasionally we dive deeper in.
This podcast updates daily.
This podcast is available on 4 platforms including Apple Podcasts, Spotify, and more. You can also use the RSS feed directly.
No, this podcast does not typically feature guests.
Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.
All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.
We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.
While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at hey@podengine.ai for prompt review and appropriate action, which may include content removal or proper attribution.
By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.