arXiv (All)
open access
Semantics as a Shield: Label Disguise Defense (LDD) against Prompt Injection in LLM Sentiment Classification
Prompt injection can cause large language models (LLMs) to deviate from their intended tasks by following instructions embedded in untrusted input. We investigate whether changing a classifier's output labels improves accuracy under such attacks, using sentiment classification as a case study. Label
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Black-Box Membership Inference via Word-Level Probability Estimation#997613
- CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?#784763
- CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?#783173
- Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2#998509
- Provenance Before Prose: Claim-Locked Reporting for Statistical Text Generation#1036765
Record · ID 1342368
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive