Image de couverture de livre

Semantics as a Shield: Label Disguise Defense (LDD) against Prompt Injection in LLM Sentiment Classification

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Yanxi, Shan, Ruocheng
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game
par: Xu, Qianqiao, et autres
Publié: (2024)

Soft Begging: Modular and Efficient Shielding of LLMs against Prompt Injection and Jailbreaking based on Prompt Tuning
par: Ostermann, Simon, et autres
Publié: (2024)

Prompt Sentiment: The Catalyst for LLM Change
par: Gandhi, Vishal, et autres
Publié: (2025)

Prompt Injection attack against LLM-integrated Applications
par: Liu, Yi, et autres
Publié: (2023)

Jatmo: Prompt Injection Defense by Task-Specific Finetuning
par: Piet, Julien, et autres
Publié: (2023)

Arabic Metaphor Sentiment Classification Using Semantic Information
par: Alsiyat, Israa
Publié: (2025)

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
par: An, Hengyu, et autres
Publié: (2025)

Formalizing and Benchmarking Prompt Injection Attacks and Defenses
par: Liu, Yupei, et autres
Publié: (2023)

FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks
par: Xu, Naen, et autres
Publié: (2026)

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents
par: Jia, Feiran, et autres
Publié: (2024)

Revisiting the Role of Label Smoothing in Enhanced Text Sentiment Classification
par: Gao, Yijie, et autres
Publié: (2023)

Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing
par: Theocharopoulos, Panagiotis, et autres
Publié: (2025)

LLM Based Sentiment Classification From Bangladesh E-Commerce Reviews
par: Tabassum, Sumaiya
Publié: (2025)

A Systematic Literature Review on LLM Defenses Against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy
par: Correia, Pedro H. Barcha, et autres
Publié: (2026)

ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack
par: Li, Hao, et autres
Publié: (2026)

Palisade -- Prompt Injection Detection Framework
par: Kokkula, Sahasra, et autres
Publié: (2024)

Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses
par: Yang, Xiaoxue, et autres
Publié: (2025)

Chain-of-Thought Unfaithfulness as Disguised Accuracy
par: Bentham, Oliver, et autres
Publié: (2024)

Style Attack Disguise: When Fonts Become a Camouflage for Adversarial Intent
par: Zhang, Yangshijie, et autres
Publié: (2025)

Implicit Sentiment Analysis Based on Chain of Thought Prompting
par: Duan, Zhihua, et autres
Publié: (2024)

PromptRad: Knowledge-Enhanced Multi-Label Prompt-Tuning for Low-Resource Radiology Report Labeling
par: Lin, Ying-Jia, et autres
Publié: (2026)

AttentionDefense: Leveraging System Prompt Attention for Explainable Defense Against Novel Jailbreaks
par: Siska, Charlotte, et autres
Publié: (2025)

MIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated Content
par: Guo, Ruoqi, et autres
Publié: (2026)

Small Language Model Helps Resolve Semantic Ambiguity of LLM Prompt
par: Huang, Zhenzhen, et autres
Publié: (2026)

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
par: Lin, Huawei, et autres
Publié: (2025)

Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction
par: Zhang, Yice, et autres
Publié: (2024)

Optimization Techniques for Sentiment Analysis Based on LLM (GPT-3)
par: Zhan, Tong, et autres
Publié: (2024)

ShieldLearner: A New Paradigm for Jailbreak Attack Defense in LLMs
par: Ni, Ziyi, et autres
Publié: (2025)

Prompt Injection as Role Confusion
par: Ye, Charles, et autres
Publié: (2026)

Certifying LLM Safety against Adversarial Prompting
par: Kumar, Aounon, et autres
Publié: (2023)

May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks
par: Pandya, Nishit V., et autres
Publié: (2025)

Enhanced Multimodal Aspect-Based Sentiment Analysis by LLM-Generated Rationales
par: Cao, Jun, et autres
Publié: (2025)

Detection Method for Prompt Injection by Integrating Pre-trained Model and Heuristic Feature Engineering
par: Ji, Yi, et autres
Publié: (2025)

CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement
par: Kholkar, Gauri, et autres
Publié: (2025)

Target-oriented Multimodal Sentiment Classification with Counterfactual-enhanced Debiasing
par: Liu, Zhiyue, et autres
Publié: (2025)

BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English
par: Srirag, Dipankar, et autres
Publié: (2024)

Deep Learning-based Sentiment Classification: A Comparative Survey
par: Kayed, Mohamed, et autres
Publié: (2023)

Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
par: Fujinuma, Yoshinari, et autres
Publié: (2026)

Systematically Analyzing Prompt Injection Vulnerabilities in Diverse LLM Architectures
par: Benjamin, Victoria, et autres
Publié: (2024)

Combining Supervised Learning and Reinforcement Learning for Multi-Label Classification Tasks with Partial Labels
par: Jia, Zixia, et autres
Publié: (2024)