SMILES-Prompting: A Novel Approach to LLM Jailbreak Attacks in Chemical Synthesis
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.
Code (1)
Tasks
LLM JailbreakRed TeamingSimilar Papers 제목 키워드 기반
Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction
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 retrosynthesisUAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment
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+1Accelerating the inference of string generation-based chemical reaction models for industrial applications
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 retrosynthesisTranslationCopy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis
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 DiscoveryA deep-learning view of chemical space designed to facilitate drug discovery
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