David Khachaturov
Scholar

David Khachaturov

Google Scholar ID: 6Lt77koAAAAJ
Computer Lab, University of Cambridge
Adversarial Machine LearningSecurityReinforcement LearningNLP
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
69
 
H-index
3
 
i10-index
2
 
Publications
11
 
Co-authors
18
list available
Contact
GitHubOpen ↗
Publications
5 items
Governments Should Mandate Tiered Anonymity on Social-Media Platforms to Counter Deepfakes and LLM-Driven Mass Misinformation
2025
Cited
0
Adversarial Suffix Filtering: a Defense Pipeline for LLMs
2025
Cited
0
Watermarking Needs Input Repetition Masking
2025
Cited
0
"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models
2025
Cited
0
Data Poisoning in LLMs: Jailbreak-Tuning and Scaling Laws
2024
Cited
6
Resume (English only)
Co-authors
18 total
Dillon Bowen
Dillon Bowen
The Wharton School of Business
Kellin Pelrine
Kellin Pelrine
FAR.AI
Will Cai
Will Cai
UC Berkeley
Adam Gleave
Adam Gleave
CEO at FAR AI
Robert Mullins
Robert Mullins
Department of Computer Science and Technology, University of Cambridge
Ilia Shumailov
Ilia Shumailov
AI Sequrity Company
Ross Anderson
Ross Anderson
University of Cambridge
Nicolas Papernot
Nicolas Papernot
University of Toronto and Vector Institute