AI safety researcher

Ivan Evtimov

Google Scholar dblp

Last 12 months6 papers

Attacks 2Other 1Evaluation and benchmarks 1

AI safety papers from the last year

On this site: 26 papers

October 2026

Muse Glimmer 30B: An On-Device Agentic Model
Oct 17OtherarXiv ↗
X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems
Oct 9AttacksarXiv ↗

September 2026

Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection
Sep 3AttacksarXiv ↗

May 2026

Muse Spark Safety & Preparedness Report
May 14arXiv ↗

March 2026

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
Mar 16Evaluation and benchmarksarXiv ↗

December 2025

Safety Alignment of LMs via Non-cooperative Games
Dec 23arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.