Andrey Labunets

Orcid: 0009-0002-7957-4631

According to our database1, Andrey Labunets authored at least 9 papers between 2021 and 2025.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks.
CoRR, July, 2025

Best Current Practice for OAuth 2.0 Security.
RFC, January, 2025

Computing Optimization-Based Prompt Injections Against Closed-Weights Models By Misusing a Fine-Tuning API.
CoRR, January, 2025

Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-Based Prompt Injection Attacks via the Fine-Tuning Interface.
Proceedings of the IEEE Symposium on Security and Privacy, 2025

An Empirical Analysis on the Use and Reporting of National Security Letters.
Proceedings of the 2025 Symposium on Computer Science and Law, 2025

2024
Experimental Analyses of the Physical Surveillance Risks in Client-Side Content Scanning.
Proceedings of the 31st Annual Network and Distributed System Security Symposium, 2024

2022
Re-purposing Perceptual Hashing based Client Side Scanning for Physical Surveillance.
CoRR, 2022

2021
Overview of Abusive and Threatening Language Detection in Urdu at FIRE 2021.
Proceedings of the Working Notes of FIRE 2021, 2021

[email protected] FIRE2021: Shared Track on Abusive Threat Identification in Urdu.
Proceedings of the FIRE 2021: Forum for Information Retrieval Evaluation, Virtual Event, India, December 13, 2021


  Loading...