AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
AI Security - Can LLM be Attacked?
Cloud Security Podcast
The Attack on the LLM Model
Backdoor attacks or the Troj AI attacks, basically the model itself could be corrupted in a way that you can leave backdoors to come back and modify the model. Data poisoning attack is on the data that is being used by the LLM model to train itself. Another form to this could also be the open source library Wonderbolty or supply chain Wonderbolty because how can you forget supply chain in this? This is also a reason for the outrage that chat GPD went through in March. And what essentially happened was they were using Redis, which is an open source for caching information.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode