Chhavi Yadav

Identifiers

• name variant Chhavi Yadav 0.60 · backfill

Papers (3)

1. Alignment Defends LLMs from Property Inference Attacks cs.LG · 2026 · author #2
2. Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks cs.LG · 2026 · author #2
3. Curriculum Learning for Safety Alignment cs.LG · 2026 · author #3

Mentions

• 2606.10217 #2 · arxiv_oai · confidence 0.70 Chhavi Yadav
• 2605.26526 #2 · arxiv_oai · confidence 0.70 Chhavi Yadav
• 2605.26315 #3 · arxiv_oai · confidence 0.70 Chhavi Yadav

Frequent Coauthors

• Virginia Smith 2 shared papers
• Kamalika Chaudhuri 1 shared papers
• Kevin Kuo 1 shared papers
• Pengrun Huang 1 shared papers
• Ruihan Wu 1 shared papers
• Sandeep Kumar 1 shared papers