Scholar
Roman Vainshtein
Google Scholar ID: IYSnEAEAAAAJ
Ph.D.
GenAI Security and Trust
Machine Learning
AutoML
Data Science
AI Robustness and Security
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
184
H-index
6
i10-index
5
Publications
20
Co-authors
0
Publications
12 items
BadEngram: Backdoor Attack on Gated Memory Components in LLMs
2026
Cited
0
An Actionable Diagnosis of Multilingual, Multi-Agent Planning Failures
2026
Cited
0
RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems
2026
Cited
0
When Scanners Lie: Evaluator Instability in LLM Red-Teaming
2026
Cited
0
Adversarial Intent is a Latent Variable: Stateful Trust Inference for Securing Multimodal Agentic RAG
2026
Cited
0
Inference-Time Backdoors via Hidden Instructions in LLM Chat Templates
2026
Cited
0
AgenTRIM: Tool Risk Mitigation for Agentic AI
2026
Cited
2
Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs
2025
Cited
0
Load more
