Scholar
Giorgio Severi
Google Scholar ID: ClHeQx0AAAAJ
Microsoft
Computer Security
Adversarial Machine Learning
AI Safety
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
708
H-index
10
i10-index
10
Publications
20
Co-authors
24
list available
Contact
Email
severi.g@northeastern.edu
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
9 items
Divide, Consult, Conquer: Capability Laundering Through Aligned LLMs
2026
Cited
0
Evading Chain-of-Thought Monitoring Through Model Poisoning
2026
Cited
0
GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt
2026
Cited
0
The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers
2026
Cited
0
A Systematization of Security Vulnerabilities in Computer Use Agents
2025
Cited
0
A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks
2025
Cited
0
Lessons From Red Teaming 100 Generative AI Products
2025
Cited
0
Model-agnostic clean-label backdoor mitigation in cybersecurity environments
arXiv.org · 2024
Cited
0
Load more
Resume (English only)
Co-authors
24 total
Alina Oprea
Northeastern University
Matthew Jagielski
Anthropic
Scott Coull
Google
Milad Nasr
OpenAI
Christopher A. Choquette-Choo
OpenAI
Cristina Nita-Rotaru
Professor, Khoury College of Computer Science, Northeastern University
Harsh Chaudhari
Northeastern University
Co-author 8
