Image de couverture de livre

Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qiu, Huming, Chen, Guanxu, Zhang, Mi, Zhang, Xiaohan, You, Xiaoyu, Yang, Min
Format:	Preprint
Publié:	2024
Sujets:	Cryptography and Security Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
par: Qiu, Huming, et autres
Publié: (2023)

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization
par: Liu, Mingshuo, et autres
Publié: (2026)

SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
par: Li, Xinfeng, et autres
Publié: (2024)

PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
par: Geng, Runpeng, et autres
Publié: (2025)

Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization
par: Cooper, Portia, et autres
Publié: (2024)

Text Embedding Inversion Security for Multilingual Language Models
par: Chen, Yiyi, et autres
Publié: (2024)

SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models
par: Liu, Renyang, et autres
Publié: (2026)

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
par: Dong, Jianshuo, et autres
Publié: (2025)

SEW: Strengthening Robustness of Black-box DNN Watermarking via Specificity Enhancement
par: Qiu, Huming, et autres
Publié: (2026)

Groot: Adversarial Testing for Generative Text-to-Image Models with Tree-based Semantic Transformation
par: Liu, Yi, et autres
Publié: (2024)

Goal-guided Generative Prompt Injection Attack on Large Language Models
par: Zhang, Chong, et autres
Publié: (2024)

XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
par: Xu, Jiahao, et autres
Publié: (2026)

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

Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation
par: Chen, Sixu, et autres
Publié: (2026)

Token-level Data Selection for Safe LLM Fine-tuning
par: Li, Yanping, et autres
Publié: (2026)

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

Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization
par: Liu, Tiantian, et autres
Publié: (2024)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
par: Yang, Wenkai, et autres
Publié: (2024)

Imitate Before Detect: Aligning Machine Stylistic Preference for Machine-Revised Text Detection
par: Chen, Jiaqi, et autres
Publié: (2024)

From Thinking to Output: Chain-of-Thought and Text Generation Characteristics in Reasoning Language Models
par: Liu, Junhao, et autres
Publié: (2025)

SciSafeEval: A Comprehensive Benchmark for Safety Alignment of Large Language Models in Scientific Tasks
par: Li, Tianhao, et autres
Publié: (2024)

Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation
par: Shahariar, G M, et autres
Publié: (2024)

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment
par: Wang, Kun, et autres
Publié: (2026)

Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations
par: Teja, Lekkala Sai, et autres
Publié: (2025)

Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation
par: Schwartz, Daniel, et autres
Publié: (2025)

SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains
par: Saiem, Bijoy Ahmed, et autres
Publié: (2024)

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

SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning
par: Zhou, Kaiwen, et autres
Publié: (2025)

DePrompt: Desensitization and Evaluation of Personal Identifiable Information in Large Language Model Prompts
par: Sun, Xiongtao, et autres
Publié: (2024)

LeakDojo: Decoding the Leakage Threats of RAG Systems
par: Zhang, Maosen, et autres
Publié: (2026)

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
par: Su, Yanghao, et autres
Publié: (2026)

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

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

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

Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in Large Language Models
par: Zheng, Yujia, et autres
Publié: (2025)

Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs
par: Kim, Jinhwa, et autres
Publié: (2025)

SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding
par: Xu, Zhangchen, et autres
Publié: (2024)

SAMark: A Self-Anchored Text Watermarking with Paragraph-Level Paraphrase Robustness
par: Huo, Jiahao, et autres
Publié: (2026)

CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
par: Zhou, Guanghao, et autres
Publié: (2025)

You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors
par: Cao, Bochuan, et autres
Publié: (2025)