mlsanityData to 14 Oct 2026

DecipherGuard: Understanding and Deciphering Jailbreak Prompts for a Safer Deployment of Intelligent Software Systems

arXiv 2509.16870 ↗First posted 21 Sep 2025cs.SE cs.CRcited by 1

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Intelligent software systems powered by Large Language Models (LLMs) are increasingly deployed in critical sectors, raising concerns about their safety during runtime. Through an industry-academic collaboration when deploying an LLM-powered virtual customer assistant, a critical software engineering challenge emerged: how to enhance a safer deployment of LLM-powered software systems at runtime? While LlamaGuard, the current state-of-the-art runtime guardrail, offers protection against unsafe inputs, our study reveals a Defense Success Rate (DSR) drop of 24% under obfuscation- and template-based jailbreak attacks. In this paper, we propose DecipherGuard, a novel framework that integrates a deciphering layer to counter obfuscation-based prompts and a low-rank adaptation mechanism to enhance guardrail effectiveness against template-based attacks. Empirical evaluation on over 22,000 prompts demonstrates that DecipherGuard improves DSR by 36% to 65% and Overall Guardrail Performance (OGP) by 20% to 50% compared to LlamaGuard and two other runtime guardrails. These results highlight the effectiveness of DecipherGuard in defending LLM-powered software systems against jailbreak attacks during runtime.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 35 of its 53 references that are in the map. First posted on arXiv 21 Sep 2025.

Builds on

35 of 53 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024Jailbreak Attacks and Defenses Against Large Language Models: A Survey5 Jul
  2. 2024JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models28 Mar
  3. 2024CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models26 Feb
  4. 2024A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models21 Feb
  5. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreaker6 Nov
  6. 2023Low-Resource Languages Jailbreak GPT-43 Oct
  7. 2023Detecting Language Model Attacks with Perplexity27 Aug
  8. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  9. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug
  10. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
  11. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul

Other references · 24

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  5. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  6. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  7. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  8. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  9. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
  10. 2020Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlationcited by 425
  11. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 387
  12. 2023NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Railscited by 365
12 more
  1. 2023Formalizing and Benchmarking Prompt Injection Attacks and Defensescited by 364
  2. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 356
  3. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 278
  4. 2023Large Language Model Alignment: A Surveycited by 243
  5. 2024Foundational Challenges in Assuring Alignment and Safety of Large Language Modelscited by 199
  6. 2022A New Generation of Perspective API: Efficient Multilingual Character-level Transformerscited by 185
  7. 2023Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMscited by 184
  8. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  9. 2024Language Models are Homer Simpson! Safety Re-Alignment of Fine-tuned Language Models through Task Arithmeticcited by 112
  10. 2024Safeguarding Large Language Models: A Surveycited by 78
  11. 2024Rethinking Software Engineering in the Foundation Model Era: From Task-Driven AI Copilots to Goal-Driven AI Pair Programmerscited by 12
  12. 2024Recent Advances in Attack and Defense Approaches of Large Language Modelscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Unread or Unenforced? Separating Representation from Enforcement Failure in Content Guardscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered Software
  2. 2025PandaGuard: Systematic Evaluation of LLM Safety against Jailbreaking Attacks
  3. 2025Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security
  4. 2025GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing
  5. 2024Defensive Prompt Patch: A Robust and Interpretable Defense of LLMs against Jailbreak Attacks
  6. 2025SoK: Evaluating Jailbreak Guardrails for Large Language Models
  7. 2025Jailbreak Distillation: Renewable Safety Benchmarking
  8. 2026CS-Guard: Benchmarking LLM Guardrails for Code Generation Security