AI safety researcher

Yevgeniy Vorobeychik

Washinton University in St. Louis

Google Scholar dblp ORCID Homepage

Last 12 months10 papers

Defenses 3Attacks 1

AI safety papers from the last year

On this site: 52 papers

October 2026

Not Where You Think: Protecting Location Privacy Against Reasoning-Based Geolocation
Oct 21DefensesarXiv ↗
AutoRedClaw: Automated Red-Teaming for Claw-Style Agents
Oct 19AttacksarXiv ↗
Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience
Oct 3DefensesarXiv ↗
Protecting Sensitive Data in Image Synthesis via PAC-Private Adaptation for Diffusion Models
Oct 2arXiv ↗
SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples
Oct 1DefensesarXiv ↗

June 2026

April 2026

Low Rank Adaptation for Adversarial Perturbation
Apr 30arXiv ↗

February 2026

AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?
Feb 3arXiv ↗

November 2025

Sliced Rényi Pufferfish Privacy: Directional Additive Noise Mechanism and Private Learning with Gradient Clipping
Nov 30arXiv ↗

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