mlsanityData to 14 Oct 2026

Self-Guard: Empower the LLM to Safeguard Itself

arXiv 2310.15851 ↗First posted 24 Oct 2023cs.CLcited by 54

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

The jailbreak attack can bypass the safety measures of a Large Language Model (LLM), generating harmful content. This misuse of LLM has led to negative societal consequences. Currently, there are two main approaches to address jailbreak attacks: safety training and safeguards. Safety training focuses on further training LLM to enhance its safety. On the other hand, safeguards involve implementing external models or filters to prevent harmful outputs. However, safety training has constraints in its ability to adapt to new attack types and often leads to a drop in model performance. Safeguards have proven to be of limited help. To tackle these issues, we propose a novel approach called Self-Guard, which combines the strengths of both safety methods. Self-Guard includes two stages. In the first stage, we enhance the model's ability to assess harmful content, and in the second stage, we instruct the model to consistently perform harmful content detection on its own responses. The experiment has demonstrated that Self-Guard is robust against jailbreak attacks. In the bad case analysis, we find that LLM occasionally provides harmless responses to harmful queries. Additionally, we evaluated the general capabilities of the LLM before and after safety training, providing evidence that Self-Guard does not result in the LLM's performance degradation. In sensitivity tests, Self-Guard not only avoids inducing over-sensitivity in LLM but also can even mitigate this issue.

Key facts. Cited by 54 papers in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 36 of its 69 references that are in the map. First posted on arXiv 24 Oct 2023.

Builds on

36 of 69 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
  2. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  3. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  4. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul
  5. 2023Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study23 May

Other references · 31

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  5. 2019HellaSwag: Can a Machine Really Finish Your Sentence?cited by 4,100
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  7. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  8. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
  9. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  10. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  11. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
  12. 2023LIMA: Less Is More for Alignmentcited by 1,100
19 more
  1. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
  2. 2022Red Teaming Language Models with Language Modelscited by 1,026
  3. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  4. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
  5. 2019Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classificationcited by 404
  6. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 365
  7. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 356
  8. 2013Good Debt or Bad Debt: Detecting Semantic Orientations in Economic Textscited by 310
  9. 2023How is ChatGPT's behavior changing over time?cited by 270
  10. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
  11. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoningcited by 194
  12. 2019A Question-Entailment Approach to Question Answeringcited by 134
  13. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 82
  14. 2022COLD: A Benchmark for Chinese Offensive Language Detectioncited by 76
  15. 2023Aligning Large Language Models through Synthetic Feedbackcited by 75
  16. 2020Effective Transfer Learning for Identifying Similar Questions: Matching User Questions to COVID-19 FAQscited by 48
  17. 2022Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarkscited by 36
  18. 2023Rethinking Machine Ethics -- Can LLMs Perform Moral Reasoning through the Lens of Moral Theories?cited by 36
  19. 2023Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysiscited by 35

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 13; 2025: 29; 2026: 12.

54 papers.

Sort:

By area:

  1. 2024AutoDefense: Multi-Agent LLM Defense against Jailbreak Attackscited by 145
  2. 2024Know Your Limits: A Survey of Abstention in Large Language Modelscited by 121
  3. 2024Red-Teaming for Generative AI: Silver Bullet or Security Theater?cited by 83
  4. 2025STAIR: Improving Safety Alignment with Introspective Reasoningcited by 77
  5. 2025OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safetycited by 75
  6. 2024Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledgecited by 51
  7. 2024Audio Is the Achilles' Heel: Red Teaming Audio Large Multimodal Modelscited by 37
  8. 2024Jailbreaking and Mitigation of Vulnerabilities in Large Language Modelscited by 34
  9. 2024AttackEval: How to Evaluate the Effectiveness of Jailbreak Attacking on Large Language Modelscited by 28
  10. 2024Mission Impossible: A Statistical Perspective on Jailbreaking LLMscited by 24
  11. 2025Inverse Reinforcement Learning with Dynamic Reward Scaling for LLM Alignmentcited by 20
  12. 2024Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Modelscited by 19
38 more
  1. 2024See What LLMs Cannot Answer: A Self-Challenge Framework for Uncovering LLM Weaknessescited by 15
  2. 2025Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviorscited by 13
  3. 2025Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behaviorcited by 12
  4. 2025From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystemcited by 12
  5. 2025Information Suppression in Large Language Models: Auditing, Quantifying, and Characterizing Censorship in DeepSeekcited by 11
  6. 2025A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attackscited by 11
  7. 2025Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerabilitycited by 10
  8. 2025The Alignment Waltz: Jointly Training Agents to Collaborate for Safetycited by 10
  9. 2025Characterizing LLM-driven Social Network: The Chirper.ai Casecited by 9
  10. 2025Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Modelscited by 9
  11. 2025Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLMcited by 9
  12. 2025PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualizationcited by 8
  13. 2025LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasurescited by 8
  14. 2025Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancementcited by 8
  15. 2025ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoningcited by 8
  16. 2025Towards the Worst-case Robustness of Large Language Modelscited by 7
  17. 2024Purple-teaming LLMs with Adversarial Defender Trainingcited by 6
  18. 2026Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projectioncited by 6
  19. 2026Sparse Autoencoders are Capable LLM Jailbreak Mitigatorscited by 6
  20. 2026Neglected Free Lunch from Post-training: Progress Advantage for LLM Agentscited by 6
  21. 2025Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Modelscited by 5
  22. 2025Do Methods to Jailbreak and Defend LLMs Generalize Across Languages?cited by 5
  23. 2024GPT in Sheep's Clothing: The Risk of Customized GPTscited by 4
  24. 2025Co-Investigator AI: The Rise of Agentic AI for Smarter, Trustworthy AML Compliance Narrativescited by 4
  25. 2025Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Modelscited by 4
  26. 2026EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibriumcited by 4
  27. 2025Toxicity in Online Platforms and AI Systems: A Survey of Needs, Challenges, Mitigations, and Future Directionscited by 3
  28. 2025Large Language Models as Search Engines: Societal Challengescited by 3
  29. 2025Learning to Extract Context for Context-Aware LLM Inferencecited by 2
  30. 2024Developing Assurance Cases for Adversarial Robustness and Regulatory Compliance in LLMscited by 1
  31. 2025A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokenscited by 1
  32. 2025MirrorShield: Towards Universal Defense Against Jailbreaks via Entropy-Guided Mirror Craftingcited by 1
  33. 2025ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstractioncited by 1
  34. 2026SpatialJB: How Text Distribution Art Becomes the "Jailbreak Key" for LLM Guardrailscited by 1
  35. 2026Do LLMs Follow Their Own Rules? A Reflexive Audit of Self-Stated Safety Policiescited by 1
  36. 2026Beyond Safe Data: Pretraining-Stage Alignment with Regular Safety Reflectioncited by 1
  37. 2026Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directionscited by 1
  38. 2025Evaluating Multi-Agent Defences Against Jailbreaking Attacks on Large Language Modelscited by 0

50 most cited of 54 All 54 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models
  2. 2025Jailbreaking Attacks vs. Content Safety Filters: How Far Are We in the LLM Safety Arms Race?
  3. 2025PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
  4. 2026Re-Triggering Safeguards within LLMs for Jailbreak Detection
  5. 2025You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense
  6. 2025SoK: Evaluating Jailbreak Guardrails for Large Language Models
  7. 2025Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions
  8. 2026SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits