Automatic and Universal Prompt Injection Attacks against Large Language Models — HN submission

Thu, 28 Aug 2025 10:10:05 GMT

Automatic and Universal Prompt Injection Attacks Against Large Language Models

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Automatic and Universal Prompt Injection Attacks against Large Language Models — mentioned by Eridrus

Sun, 16 Mar 2025 16:41:19 GMT

I applaud you for trying to tackle this, but after reading your docs a little I am skeptical of your approach. Your example of having a rule saying that the user's email address is not put in a search query seems to have two problems: a) non-LLM models can be bypassed by telling LLMs to encode the email tokens, trivially ROT13, or many other encoding schemes b) the LLM checkers suffer from the same prompt injection problems In particular, gradient-based methods are unsurprisingly a lot better at defeating all the proposed mitigations, e.g. https://arxiv.org/abs/2403.04957 For now I think the…

Paper and discussion history. A mention is not an endorsement.

Automatic and Universal Prompt Injection Attacks against Large Language Models · HackerPapers discussions

Automatic and Universal Prompt Injection Attacks against Large Language Models — HN submission

Automatic and Universal Prompt Injection Attacks against Large Language Models — mentioned by Eridrus