Frontier large language models (LLMs) are increasingly integrated into scientific workflows, yet their growing biological capabilities may outpace current safeguards. To assess the biological risks of frontier models, we develop Intern-BioBreaker, a specialized bio-red-teaming model, together with an integrated computational-to-physical framework that couples model-level stress testing with wet-lab validation.
arXiv:2608. 02684v1 Announce Type: cross Abstract: Large Language Models (LLMs) are accelerating biological research, yet this same capability poses a critical biosecurity threat: models that assist in protein engineering can equally be prompted to generate predicted toxin-like sequences, potentially lowering the barrier to biological misuse.
By Shu Quan, Tianfang Hao, Sitong Fang, He Geng, Jiayi Zhou, Boyuan Chen, Kaile Wang, Donghai Hong, Juntao Dai, Yaodong Yang, Jiaming Ji
arXiv:2504. 17247v3 Announce Type: replace Abstract: Deep learning-based antimicrobial peptide (AMP) discovery faces critical challenges such as limited controllability, lack of representations that efficiently model antimicrobial properties, and low experimental hit rates.
By Diogo Soares, Leon Hetzel, Paulina Szymczak, Marcelo Der Torossian Torres, Johanna Sommer, Cesar de la Fuente-Nunez, Fabian Theis, Stephan G\"unnemann, Ewa Szczurek
arXiv:2606. 17127v1 Announce Type: cross Abstract: Antimicrobial resistance causes to over a million deaths annually.
By Jay Jung, Xiaohan Zhang, Shenghan Song, Mahmoud Sayedahmed, Chijian Xiang, Yunong Xu, Ahmed AbdelKhalek, Severin T. Schneebeli, Matthew J. Wargo, Jianing Li, Safwan Wshah
arXiv:2606. 07992v1 Announce Type: new Abstract: As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-handling loop.
By Harshil Patel, Kunal Pai
arXiv:2606. 01816v1 Announce Type: cross Abstract: Selecting where to intervene on a protein (i.
By Taehan Kim, Sarrah Rose Mikhail Leung, Bharat Mekala, Jeongbin Park
arXiv:2607. 08404v1 Announce Type: cross Abstract: Current computational approaches for drug design typically focus on generating molecules conditioned on specific targets or general molecular properties, often neglecting the influence of disease context on target behavior and therapeutic outcomes.
By Ali Motahharynia, Mohammadreza Ghaffarzadeh-Esfahani, Mahsa Sheikholeslami, Navid Mazrouei, Matin Irajpour, Yousof Gheisari, Hajar Sirous
arXiv:2607. 00464v1 Announce Type: new Abstract: Current molecular generation benchmarks emphasize task complexity, molecule novelty, and property alignment; they largely overlook a critical concern: the potential safety risks of AI-generated molecules.
By Tong Xu, Xinzhe Cao, Zhihui Zhu, Keyan Ding, Huajun Chen
We’re developing a blueprint for evaluating the risk that a large language model (LLM) could aid someone in creating a biological threat. In an evaluation involving both biology experts and students, we found that GPT-4 provides at most a mild uplift in biological threat creation accuracy.
arXiv:2603. 10302v3 Announce Type: replace Abstract: A plethora of protein language models have been released in recent years.
By Calvin McCarter, Nick Bhattacharya, Sebastian W. Ober, Hunter Elliott
Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can generate adversary-chosen content. Existing defenses target backdoors one at a time and typically require knowledge of the trigger, leaving the defender at a structural disadvantage when unknown backdoors may exist in a model.
arXiv:2602. 01051v5 Announce Type: replace Abstract: Repertoire-level analysis of T cell receptors offers a biologically grounded signal for disease detection and immune monitoring, yet practical deployment is impeded by label sparsity, cohort heterogeneity, and the computational burden of adapting large encoders to new tasks.
By Rong Fu, Muge Qi, Yang Li, Yabin Jin, Jiekai Wu, Chunlei Meng, Juntao Gao, Li Bao, Qi Zhao, Wei Luo, Youjin Wang, Simon Fong