Cover Image

Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Zhan, Huixin
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning Quantitative Methods
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Transformers in Protein: A Survey
by: Ling, Xiaowen, et al.
Published: (2025)

Federated unsupervised random forest for privacy-preserving patient stratification
by: Pfeifer, Bastian, et al.
Published: (2024)

SafeProtein: Red-Teaming Framework and Benchmark for Protein Foundation Models
by: Fan, Jigang, et al.
Published: (2025)

Integrating MLSecOps in the Biotechnology Industry 5.0
by: Pervez, Naseela, et al.
Published: (2024)

FedRBE -- a decentralized privacy-preserving federated batch effect correction tool for omics data based on limma
by: Burankova, Yuliya, et al.
Published: (2024)

Adaptive Federated Few-Shot Rare-Disease Diagnosis with Energy-Aware Secure Aggregation
by: Aueawatthanaphisut, Aueaphum
Published: (2025)

Scaling Up ESM2 Architectures for Long Protein Sequences Analysis: Long and Quantized Approaches
by: de Oliveira, Gabriel Bianchin, et al.
Published: (2025)

Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning
by: Nguyen, Quan Minh, et al.
Published: (2026)

Privacy-Preserving Collaborative Medical Image Segmentation Using Latent Transform Networks
by: Bello, Saheed Ademola, et al.
Published: (2026)

ESM-NBR: fast and accurate nucleic acid-binding residue prediction via protein language model feature representation and multi-task learning
by: Zeng, Wenwu, et al.
Published: (2023)

ImmSET: Sequence-Based Predictor of TCR-pMHC Specificity at Scale
by: Noceda, Marco Garcia, et al.
Published: (2026)

Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
by: Zhan, Qiusi, et al.
Published: (2025)

SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking
by: Yang, Wenyuan, et al.
Published: (2025)

Agentic Discovery of Cryomicroneedle Formulations
by: Li, Hao, et al.
Published: (2026)

A Modular Open Source Framework for Genomic Variant Calling
by: Bisoi, Ankita Vaishnobi, et al.
Published: (2024)

Auditing Privacy Mechanisms via Label Inference Attacks
by: Busa-Fekete, Róbert István, et al.
Published: (2024)

Multimodal Survival Modeling and Fairness-Aware Clinical Machine Learning for 5-Year Breast Cancer Risk Prediction
by: Khatibi, Toktam
Published: (2026)

Molecular Lead Optimization via Agentic Tool Planning
by: Li, Lingxiao, et al.
Published: (2026)

CacheProbe: Auditing Prompt Cache Isolation in Gateway APIs
by: Fahey, Ryan
Published: (2026)

Checkpoint-GCG: Auditing and Attacking Fine-Tuning-Based Prompt Injection Defenses
by: Yang, Xiaoxue, et al.
Published: (2025)

Know Your Scientist: KYC as Biosecurity Infrastructure
by: Feldman, Jonathan, et al.
Published: (2026)

BOAT: Navigating the Sea of In Silico Predictors for Antibody Design via Multi-Objective Bayesian Optimization
by: Rao, Jackie, et al.
Published: (2026)

Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows
by: Otun, Martins
Published: (2026)

Protenix-Mini: Efficient Structure Predictor via Compact Architecture, Few-Step Diffusion and Switchable pLM
by: Gong, Chengyue, et al.
Published: (2025)

Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors
by: Kim, Hyeonah, et al.
Published: (2026)

SOS! Soft Prompt Attack Against Open-Source Large Language Models
by: Yang, Ziqing, et al.
Published: (2024)

Beyond Manual Curation: Augmenting Targeted Protein Degradation Databases via Agentic Literature Extraction Workflows
by: Rao, Yaochen, et al.
Published: (2026)

Few-Label Multimodal Modeling of SNP Variants and ECG Phenotypes Using Large Language Models for Cardiovascular Risk Stratification
by: Menon, Niranjana Arun, et al.
Published: (2025)

DPASyn: Mechanism-Aware Drug Synergy Prediction via Dual Attention and Precision-Aware Quantization
by: Nie, Yuxuan, et al.
Published: (2025)

Auditable Early Stopping for Agentic Routing: Ledger-Verified Run-Wise Certificates under Local DP
by: Akhauri, Shivam
Published: (2025)

Resilient Biosecurity in the Era of AI-Enabled Bioweapons
by: Feldman, Jonathan, et al.
Published: (2025)

Adversarial Prompt Evaluation: Systematic Benchmarking of Guardrails Against Prompt Input Attacks on LLMs
by: Zizzo, Giulio, et al.
Published: (2025)

Are You Using Reliable Graph Prompts? Trojan Prompt Attacks on Graph Neural Networks
by: Lin, Minhua, et al.
Published: (2024)

Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries
by: Laws, Matthew D., et al.
Published: (2026)

Towards AI-Based Precision Oncology: A Machine Learning Framework for Personalized Counterfactual Treatment Suggestions based on Multi-Omics Data
by: Schürch, Manuel, et al.
Published: (2024)

FARM: Enhancing Molecular Representations with Functional Group Awareness
by: Nguyen, Thao, et al.
Published: (2024)

Exact Soft Analytical Side-Channel Attacks using Tractable Circuits
by: Wedenig, Thomas, et al.
Published: (2025)

Donor-Aware scRNA-seq Benchmarks for IBD Classification
by: Muhire, Jonathan
Published: (2026)

Auditing Prompt Caching in Language Model APIs
by: Gu, Chenchen, et al.
Published: (2025)

PA-MIL: Phenotype-Aware Multiple Instance Learning Guided by Language Prompting and Genotype-to-Phenotype Relationships
by: Yang, Zekang, et al.
Published: (2026)