Introduces six-dimension trustworthiness definition and attention-based A-Trust score with a TMS to improve LLM-MAS robustness against malicious or unreliable messages.
Why are my prompts leaked? unraveling prompt extraction threats in customized large language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CR 3verdicts
UNVERDICTED 3representative citing papers
Large-scale empirical study finds widespread prompt leaking in commercial LLM apps and introduces AREA defense that improves usability while resisting leaks.
SLIP combines a soft label mechanism with key-extraction-guided CoT to reduce instruction backdoor attack success rate to 25.13% and raise clean accuracy to 87.15% in LLM agents.
citing papers explorer
-
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
Introduces six-dimension trustworthiness definition and attention-based A-Trust score with a TMS to improve LLM-MAS robustness against malicious or unreliable messages.
-
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications
Large-scale empirical study finds widespread prompt leaking in commercial LLM apps and introduces AREA defense that improves usability while resisting leaks.
-
SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
SLIP combines a soft label mechanism with key-extraction-guided CoT to reduce instruction backdoor attack success rate to 25.13% and raise clean accuracy to 87.15% in LLM agents.