mlsanityData to 14 Oct 2026

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

arXiv 2606.00654 ↗First posted 30 May 2026cs.CRcited by 0

On the map: LLM safety and security → Backdoor and data poisoning attacks

Abstract (arXiv)

Current backdoor attacks against LLMs are typically manipulated by the attacker and remain passive. In this paper, we introduce the Proactive Availability Backdoor (PAB), a novel paradigm that shifts the attack vector from passive waiting to active social engineering. By weaponizing the inherent helpfulness of aligned LLMs, PAB proactively traps users into executing trigger-implanted queries by offering suggestions, achieving high aggressiveness, precision and stealthiness. To rigorously evaluate its threat in a real-life context, we introduce a dual-agent ecological simulation framework based on selected dimensions of the Five-Factor Model, and deploy PAB with few-shot prompts. Being validated on different models and domains, PAB performs remarkably and its effective attack success rate, which calculates the joint probability of attack incidence rate and attack success rate, goes to 73.1%. We also introduce Anti-PAB, a defense method tailored for PAB. Our findings reveal that the helpfulness of LLMs can be weaponized to compromise availability, exposing a serious hidden threat to LLMs users. We release all the scripts and datasets in the experiments at texttthttps://anonymous.4open.science/r/PAB-ANONYMOUS/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Backdoor and data poisoning attacks, one of 12 directions in LLM safety and security. Builds on 34 of its 49 references that are in the map. First posted on arXiv 30 May 2026.

Builds on

34 of 49 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training1 Nov
  2. 2024BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language Models23 Aug
  3. 2024Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models10 Jun
  4. 2024BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models20 Jan
  5. 2024Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning11 Jan
  6. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger26 May

Other references · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  6. 2020Extracting Training Data from Large Language Modelscited by 2,189
  7. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  8. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  9. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  10. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
  11. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 629
  12. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMscited by 573
16 more
  1. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  2. 2020Input-Aware Dynamic Backdoor Attackcited by 313
  3. 2024PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Modelscited by 267
  4. 2020ONION: A Simple and Effective Defense Against Textual Backdoor Attackscited by 263
  5. 2019A backdoor attack against LSTM-based text classification systemscited by 227
  6. 2020BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvementscited by 211
  7. 2023Personality Traits in Large Language Modelscited by 169
  8. 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 151
  9. 2023Co-Writing with Opinionated Language Models Affects Users' Viewscited by 148
  10. 2023Universal Jailbreak Backdoors from Poisoned Human Feedbackcited by 128
  11. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 123
  12. 2019Proactive Human-Machine Conversation with Explicit Conversation Goalscited by 88
  13. 2025Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrencycited by 17
  14. 2026SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attackscited by 12
  15. 2025TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agentcited by 9
  16. 2025Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attackcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs
  2. 2024Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
  3. 2023A Comprehensive Overview of Backdoor Attacks in Large Language Models within Communication Networks
  4. 2024Exploring Backdoor Vulnerabilities of Chat Models
  5. 2026The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
  6. 2025The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise
  7. 2025Rethinking Reasoning: A Survey on Reasoning-based Backdoors in LLMs
  8. 2025Proactive defense against LLM Jailbreak