Kellin Pelrine
Scholar

Kellin Pelrine

Google Scholar ID: _s2HT_0AAAAJ
FAR.AI
AI SecurityAI Agents
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
692
 
H-index
10
 
i10-index
10
 
Publications
20
 
Co-authors
68
list available
Contact
No contact links provided.
Publications
17 items
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
2026
Cited
0
Concept Influence: Leveraging Interpretability to Improve Performance and Efficiency in Training Data Attribution
2026
Cited
0
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
2026
Cited
1
Large language models can effectively convince people to believe conspiracies
arXiv.org · 2026
Cited
0
Emergent Persuasion: Will LLMs Persuade Without Being Prompted?
2025
Cited
0
$ exttt{BluePrint}$: A Social Media User Dataset for LLM Persona Evaluation and Training
2025
Cited
0
CrediBench: Building Web-Scale Network Datasets for Information Integrity
2025
Cited
0
Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility
2025
Cited
0
Resume (English only)
Co-authors
68 total
Reihaneh Rabbany
Reihaneh Rabbany
Assistant Professor of Computer Science, McGill University; Canada CIFAR AI Chair, Mila
Jean-Francois Godbout
Jean-Francois Godbout
University of Montreal
Adam Gleave
Adam Gleave
CEO at FAR AI
Zachary Yang
Zachary Yang
PhD Student, McGill University, School of Computer Science
Co-author 5
Co-author 5
Yu, Hao
Yu, Hao
McGill University, Mila
Dillon Bowen
Dillon Bowen
The Wharton School of Business
Co-author 8
Co-author 8