Toward Reliable, Safe, and Secure LLMs for Scientific Applications

Computer Science > Cryptography and Security [Submitted on 18 Mar 2026] Toward Reliable, Safe, and Secure LLMs for Scientific Applications Saket Sanjeev Chaturvedi, Joshua Bergerson, Tanwi Mallick As large language models (LLMs) evolve into autonomous "AI scientists," they promise transformative advances but introduce novel vulnerabilities, from potential "biosafety risks" to "dangerous explosions." Ensuring trustworthy deployment in science requires a new paradigm centered on reliability (ensuring factual accuracy and reproducibility), safety (preventing unintentional physical or biological harm), and security (preventing malicious misuse). Existing general-purpose safety benchmarks are poorly suited for this purpose, suffering from a fundamental domain mismatch, limited threat coverage of science-specific vectors, and benchmark overfitting, which create a critical gap in vulnerability evaluation for scientific applications. This paper examines the unique security and safety landscape of LLM agents in science. We begin by synthesizing a detailed taxonomy of LLM threats contextualized for scientific research, to better understand the unique risks associated with LLMs in science. Next, we conceptualize a mechanism to address the evaluation gap by utilizing dedicated multi-agent systems for the automated generation of domain-specific adversarial security benchmarks. Based on our analysis, we outline how existing safety methods can be brought together and integrated into a conceptual multilayered defense framework designed to combine a red-teaming exercise and external boundary controls with a proactive internal Safety LLM Agent. Together, these conceptual elements provide a necessary structure for defining, evaluating, and creating comprehensive defense strategies for trustworthy LLM agent deployment in scientific disciplines. Subjects: Cryptography and Security (cs.CR); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2603.18235 [cs.CR]   (or arXiv:2603.18235v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2603.18235 Focus to learn more Submission history From: Saket Chaturvedi [view email] [v1] Wed, 18 Mar 2026 19:43:38 UTC (548 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)