{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/smiles-prompting-a-novel-approach-to-llm","title":"SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis","arxiv_id":"2410.15641","date":"2024-10-21","proceeding":null,"authors":["Aidan Wong","He Cao","Zijing Liu","Yu Li"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2410.15641v1","url_pdf":"https://arxiv.org/pdf/2410.15641v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"smiles-prompting-a-novel-approach-to-llm","repo_url":"https://github.com/IDEA-XL/ChemSafety","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"llm-jailbreak","task_name":"LLM Jailbreak"},{"task_slug":"red-teaming","task_name":"Red Teaming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}