← Search

Kyle Jackson

2 accepted papers

2025

Defense against Prompt Injection Attacks via Mixture of Encodings

NAACL 2025short

Large Language Models (LLMs) have emerged as a dominant approach for a wide range of NLP tasks, with their access to external information further enhancing their capabilities. However, this introduces new vulnerabilities, known as prompt injection attacks, where external content embeds malicious ins…

2025

Jailbreak Distillation: Renewable Safety Benchmarking

EMNLP 2025

Large language models (LLMs) are rapidly deployed in critical applications, raising urgent needs for robust safety benchmarking. We propose Jailbreak Distillation (JBDistill), a novel benchmark construction framework that “distills” jailbreak attacks into high-quality and easily-updatable safety ben

Cited by 0SourcePDFScholar