paper-with-me

홈 › Papers

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

2024-10-21 · Aidan Wong, He Cao, Zijing Liu, Yu Li

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.

📄 PDF Abstract BibTeX arXiv:2410.15641

Code (1)

IDEA-XL/ChemSafety 공식 구현

Tasks

LLM JailbreakRed Teaming

Similar Papers 제목 키워드 기반

Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction

2022-03-22 · Zipeng Zhong, Jie Song, Zunlei Feng, Tiantao Liu 외

Chemical reaction prediction, involving forward synthesis and retrosynthesis prediction, is a fundamental problem in organic synthesis. A popular computational paradigm formulates synthesis prediction as a sequence-to-se…

Chemical Reaction PredictionPredictionRetrosynthesisSingle-step retrosynthesis

UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment

2024-03-25 · Kaipeng Zeng, Bo Yang, Xin Zhao, Yu Zhang 외

Motivation: Retrosynthesis planning poses a formidable challenge in the organic chemical industry. Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recen…

Graph-to-Sequencemolecular representationRepresentation LearningRetrosynthesis+1

Accelerating the inference of string generation-based chemical reaction models for industrial applications

2024-07-12 · Mikhail Andronov, Natalia Andronova, Michael Wand, Jürgen Schmidhuber 외

Template-free SMILES-to-SMILES translation models for reaction prediction and single-step retrosynthesis are of interest for industrial applications in computer-aided synthesis planning systems due to their state-of-the-…

PredictionRetrosynthesisSingle-step retrosynthesisTranslation

Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis

2025-10-18 · Jiaxi Zhuang, Yu Zhang, Aimin Zhou, Ying Qian arxiv

Retrosynthesis prediction is fundamental to drug discovery and chemical synthesis, requiring the identification of reactants that can produce a target molecule. Current template-free methods struggle to capture the struc…

Drug Discovery

A deep-learning view of chemical space designed to facilitate drug discovery

2020-02-07 · Paul Maragakis, Hunter Nisonoff, Brian Cole, David E. Shaw

Drug discovery projects entail cycles of design, synthesis, and testing that yield a series of chemically related small molecules whose properties, such as binding affinity to a given target protein, are progressively ta…

Design SynthesisDrug Discovery