anonymous.4open.science

• The Invitation Trap: Proactive Availability Backdoor in LLMs via Conversational Induction

  The Invitation Trap: Proactive Availability Backdoor in LLMs via Conversational Induction arXiv:2606.00654v1 Announce Type: new Abstract: Current backdoor attacks against LLMs are typically manipulated by the attacker and remain passive. In this paper, we introduce the \textbf{P

• Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems

  Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems arXiv:2606.18310v1 Announce Type: new Abstract: Injecting malicious knowledge into retrieval-augmented generation (RAG) systems can manipulate retrieved evidence and mislead downstream gene

All reports →

• Connector · intel_report_ingest2