POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models

Documenti analoghi

• Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks
  di: Young, Richard J.
  Pubblicazione: (2025)
• ConfusionPrompt: Practical Private Inference for Online Large Language Models
  di: Mai, Peihua, et al.
  Pubblicazione: (2023)
• UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation
  di: Geng, Runpeng, et al.
  Pubblicazione: (2025)
• DWFS-Obfuscation: Dynamic Weighted Feature Selection for Robust Malware Familial Classification under Obfuscation
  di: Wei, Xingyuan, et al.
  Pubblicazione: (2025)
• Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)
  di: Verma, Apurv, et al.
  Pubblicazione: (2024)