A new mechanism-oriented taxonomy of indirect linguistic encoding improves LLM-based coded language detection by 4.7% accuracy and 5.4% F1 on 2000 manually annotated TikTok and Bluesky posts over existing taxonomies.
Combating adversarial misspellings with robust word recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.
citing papers explorer
-
Beyond Surface Forms: A Comprehensive, Mechanism-Oriented Taxonomy of Indirect Linguistic Encoding for LLM-Based Coded Language Detection
A new mechanism-oriented taxonomy of indirect linguistic encoding improves LLM-based coded language detection by 4.7% accuracy and 5.4% F1 on 2000 manually annotated TikTok and Bluesky posts over existing taxonomies.
-
SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks
SmoothLLM mitigates jailbreaking attacks on LLMs by randomly perturbing multiple copies of a prompt at the character level and aggregating the outputs to detect adversarial inputs.