2026
Comparative Analysis of Inference-Time Defense Methods for Multimodal Large Language Models
Bulat Nutfullin, Vladimir Evgrafov, Dmitry Namiot · arXiv preprint
Research & Publications
Research interests: LLM agent security, attacks on language models and defenses against them, multimodal models, and spiking neural networks. Each paper has its own page with a short summary.
Full list and citation metrics on Google Scholar.
LLM Security · Multimodal Models
2026
Attack Methods and Defenses in LLM-Based Agentic Systems
VA Evgrafov, BM Nutfullin, DE Namiot · International Journal of Open Information Technologies 14 (5), 1-8
2023
A Review of Potential Risks of Systems with Multimodal Language Models
B Nutfullin, V Evgrafov · Tikhonov Readings, 121
Earlier Work · Spiking Neural Networks
2021
Spiking Neural Networks
VA Evgrafov, EA Ilyushin · International Journal of Open Information Technologies 9 (7), 21-31
2021
Spiking ANN Architectures and Training Methods
VA Evgrafov, EA Ilyushin · Lomonosov Readings, 70-71