mlsanityData to 14 Oct 2026

SPIN: Self-Supervised Prompt INjection

arXiv 2410.13236 ↗First posted 17 Oct 2024cs.CL cs.AIcited by 2

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Large Language Models (LLMs) are increasingly used in a variety of important applications, yet their safety and reliability remain as major concerns. Various adversarial and jailbreak attacks have been proposed to bypass the safety alignment and cause the model to produce harmful responses. We introduce Self-supervised Prompt INjection (SPIN) which can detect and reverse these various attacks on LLMs. As our self-supervised prompt defense is done at inference-time, it is also compatible with existing alignment and adds an additional layer of safety for defense. Our benchmarks demonstrate that our system can reduce the attack success rate by up to 87.9%, while maintaining the performance on benign user requests. In addition, we discuss the situation of an adaptive attacker and show that our method is still resilient against attackers who are aware of our defense.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 25 of its 31 references that are in the map. First posted on arXiv 17 Oct 2024.

Builds on

25 of 31 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs12 Jan
  2. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations10 Oct
  3. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  4. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  6. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul
  7. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May

Other references · 18

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  5. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  6. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  7. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
  8. 2023Large Language Modelscited by 780
  9. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  10. 2023ViperGPT: Visual Inference via Python Execution for Reasoningcited by 603
  11. 2018Scalable agent alignment via reward modeling: a research directioncited by 447
  12. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 278
6 more
  1. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
  2. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 234
  3. 2023RAIN: Your Language Models Can Align Themselves without Finetuningcited by 157
  4. 2023Fundamental Limitations of Alignment in Large Language Modelscited by 155
  5. 2023Summary of ChatGPT-Related Research and Perspective Towards the Future of Large Language Modelscited by 154
  6. 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Promptcited by 15
  2. 2026Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection Attackscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Jailbreaking and Mitigation of Vulnerabilities in Large Language Models
  2. 2024Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing
  3. 2024Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs
  4. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey
  5. 2024Automatic and Universal Prompt Injection Attacks against Large Language Models
  6. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily
  7. 2025Layer-Level Self-Exposure and Patch: Affirmative Token Mitigation for Jailbreak Attack Defense
  8. 2025A Critical Evaluation of Defenses against Prompt Injection Attacks