mlsanityData to 7 Oct 2026

SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis

arXiv 2410.15641 ↗First posted 21 Oct 2024cs.CLcited by 7

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

The increasing integration of large language models (LLMs) across various fields has heightened concerns about their potential to propagate dangerous information. This paper specifically explores the security vulnerabilities of LLMs within the field of chemistry, particularly their capacity to provide instructions for synthesizing hazardous substances. We evaluate the effectiveness of several prompt injection attack methods, including red-teaming, explicit prompting, and implicit prompting. Additionally, we introduce a novel attack technique named SMILES-prompting, which uses the Simplified Molecular-Input Line-Entry System (SMILES) to reference chemical substances. Our findings reveal that SMILES-prompting can effectively bypass current safety mechanisms. These findings highlight the urgent need for enhanced domain-specific safeguards in LLMs to prevent misuse and improve their potential for positive social impact.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 25 of its 30 references that are in the map. First posted on arXiv 21 Oct 2024.

Builds on

25 of 30 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization15 Nov
  2. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreaker6 Nov
  3. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  4. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations10 Oct
  5. 2023GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher12 Aug
  6. 2023"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models7 Aug
  7. 2023Latent Jailbreak: A Benchmark for Evaluating Text Safety and Output Robustness of Large Language Models17 Jul

Other references · 18

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  3. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  4. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  5. 2022Red Teaming Language Models with Language Modelscited by 983
  6. 2022Ignore Previous Prompt: Attack Techniques For Language Modelscited by 760
  7. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
  8. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  9. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 609
  10. 2023Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attackscited by 268
  11. 2023Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignmentcited by 213
  12. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 124
6 more
  1. 2024ChemLLM: A Chemical Large Language Modelcited by 100
  2. 2023FLIRT: Feedback Loop In-context Red Teamingcited by 81
  3. 2023Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilitiescited by 76
  4. 2021Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasurescited by 69
  5. 2023Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competitioncited by 65
  6. 2023BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13Bcited by 35

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challengescited by 14
  2. 2025AntiDote: Bi-level Adversarial Training for Tamper-Resistant LLMscited by 4
  3. 2026SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safetycited by 1
  4. 2025The Dual-use Dilemma in LLMs: Do Empowering Ethical Capacities Make a Degraded Utility?cited by 0
  5. 2026Malicious Repurposing of Open Science Artefacts by Using Large Language Modelscited by 0
  6. 2026onepot-Bench 0: towards lab-aware in silico chemistry benchmarkscited by 0
  7. 2026SafeMol: Dual-Modality Safety Alignment for Molecular Multimodal Modelscited by 0