Ideas & society2023 · shared on Hacker News
Universal and Transferable Adversarial Attacks on LLM
Explore Universal and Transferable Adversarial Attacks on LLM, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ywhoami_nr ·
Attacks on machine learning models
103 points38 comments
Ythatjoeoverthr ·
Prompting by Activation Maximization
14 points11 comments
Y_______W_______ ·
Destroy Humanity Tutorial (ChatGPT Jailbreak)
3 points1 comments
Ydiogotozzi ·
Universal and Transferable Adversarial Attacks on LLM
2 points0 comments
Yjackson-mcd ·
Data exfiltration from Writer.com with indirect prompt injection
2 points0 comments
Ysimon_acca ·
Universal and Transferable Adversarial Attacks on Aligned Language Models
1 points0 comments