A dual-channel detector combining DeBERTa and heuristic rules is claimed to beat existing prompt injection detectors on three benchmarks and to reduce attack success on GLM-4, Llama 3, Qwen 2.5, and GPT-4o.
Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Prompt injection (both direct and indirect) and jailbreaking are now recognized as significant issues for large language models (LLMs), particularly due to their potential for harm in application-integrated contexts. This extended abstract explores a novel approach to protecting LLMs from such attacks, termed "soft begging." This method involves training soft prompts to counteract the effects of corrupted prompts on the LLM's output. We provide an overview of prompt injections and jailbreaking, introduce the theoretical basis of the "soft begging" technique, and discuss an evaluation of its effectiveness.
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Detection Method for Prompt Injection by Integrating Pre-trained Model and Heuristic Feature Engineering
A dual-channel detector combining DeBERTa and heuristic rules is claimed to beat existing prompt injection detectors on three benchmarks and to reduce attack success on GLM-4, Llama 3, Qwen 2.5, and GPT-4o.