mlsanityData to 14 Oct 2026

Attacks on Third-Party APIs of Large Language Models

arXiv 2404.16891 ↗First posted 24 Apr 2024cs.CR cs.AI cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

Large language model (LLM) services have recently begun offering a plugin ecosystem to interact with third-party API services. This innovation enhances the capabilities of LLMs, but it also introduces risks, as these plugins developed by various third parties cannot be easily trusted. This paper proposes a new attacking framework to examine security and safety vulnerabilities within LLM platforms that incorporate third-party services. Applying our framework specifically to widely used LLMs, we identify real-world malicious attacks across various domains on third-party APIs that can imperceptibly modify LLM outputs. The paper discusses the unique challenges posed by third-party API integration and offers strategic possibilities to improve the security and safety of LLM ecosystems moving forward. Our code is released at https://github.com/vk0812/Third-Party-Attacks-on-LLMs.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 24 Apr 2024.

Builds on

18 of 23 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2018Deep contextualized word representationscited by 2,290
  7. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  8. 2023Large Language Modelscited by 780
  9. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  10. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  11. 2023DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Modelscited by 518
  12. 2020BERT-ATTACK: Adversarial Attack Against BERT Using BERTcited by 491
6 more
  1. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  2. 2016NewsQA: A Machine Comprehension Datasetcited by 331
  3. 2023An LLM can Fool Itself: A Prompt-Based Adversarial Attackcited by 116
  4. 2023From Prompt Injections to SQL Injection Attacks: How Protected is Your LLM-Integrated Web Application?cited by 55
  5. 2023LLM Platform Security: Applying a Systematic Evaluation Framework to OpenAI's ChatGPT Pluginscited by 51
  6. 2023LLMDet: A Third Party Large Language Models Generated Text Detection Toolcited by 45

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 7.

15 papers.

Sort:

By area:

  1. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  2. 2025Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Toolscited by 24
  3. 2025Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystemcited by 19
  4. 2026From Storage to Steering: Memory Control Flow Attacks on LLM Agentscited by 19
  5. 2024Analysing the Residual Stream of Language Models Under Knowledge Conflictscited by 17
  6. 2025Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Riskcited by 13
  7. 2024DAWN: Designing Distributed Agents in a Worldwide Networkcited by 6
  8. 2025Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implicationscited by 5
  9. 2026Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methodscited by 3
  10. 2026When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agentscited by 3
  11. 2025A Large-Scale Empirical Analysis of Custom GPTs' Vulnerabilities in the OpenAI Ecosystemcited by 1
  12. 2026StackingNet: Collective Inference Across Independent AI Foundation Modelscited by 0
3 more
  1. 2026Learning to Solve Complex Problems via Dataset Decompositioncited by 0
  2. 2026Security Attack and Defense Strategies for Autonomous Agent Frameworks: A Layered Review with OpenClaw as a Case Studycited by 0
  3. 2026Beware EviLLM: Enabling Vulnerability Injection via Large Language Modelscited by 0