Publication
Steering Vectors are an Adversarial Attack Surface
Jun 4, 2026 · arXiv (Cornell University)
OpenAlex citations: 0Open
Public profile
Abzal Aidakhmetov
@theballer
Machine Learning Engineer interested in doing AI Safety research, currently studying master's in Data Science at Sapienza University of Rome.
Rome, ItalySapienza University of Rome
Featured
A few things that best show this member's work and contribution.
Looking to connect
Gain and share knowledge, meet new people and possibly find a job.
Research and publications
A compact preview of this member's public research layer.
Adversarial Attacks in LLMs
AI SafetyAdversarial AttacksInterpretability