Chawin Sitawarin
Scholar

Chawin Sitawarin

Google Scholar ID: AxUAEQ4AAAAJ
Google DeepMind
machine learningartificial intelligencesecurityprivacyadversarial examples
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
2,263
 
H-index
19
 
i10-index
23
 
Publications
20
 
Co-authors
66
list available
Contact
CVOpen ↗TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
8 items
Soft Instruction De-escalation Defense
2025
Cited
0
Extracting alignment data in open models
2025
Cited
0
The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
2025
Cited
0
Does More Inference-Time Compute Really Help Robustness?
2025
Cited
0
Defending Against Prompt Injection With a Few DefensiveTokens
2025
Cited
0
How much do language models memorize?
2025
Cited
0
Lessons from Defending Gemini Against Indirect Prompt Injections
2025
Cited
0
JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift
2025
Cited
0
Resume (English only)
Co-authors
66 total
David Wagner
David Wagner
Professor of Computer Science, UC Berkeley
Prateek Mittal
Prateek Mittal
Professor, Princeton University
Arjun Bhagoji
Arjun Bhagoji
Assistant Professor, IIT Bombay
Co-author 4
Co-author 4
Julien Piet
Julien Piet
UC Berkeley
Co-author 6
Co-author 6
Sizhe Chen
Sizhe Chen
UC Berkeley, Meta FAIR
Vikash Sehwag
Vikash Sehwag
Google Deepmind; Princeton University