English

Artificial Intelligence research

What AI tools are, how they work, where your data goes, and how to use and build them responsibly at work.

Our articles on Artificial Intelligence →

Filters
Format
Peer review
Publisher
Added

1 entry

  • Journal article
  • Peer reviewed

Dynamic defence uses a model’s own layers to resist LLM jailbreaks

Original title: Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs

An AAAI conference paper introduces a method that generates defensive embeddings from a model's own layers to resist jailbreak attacks.

Doniyorkhon Obidov et al. · Added · Released Mar 2026