Atoosa Chegini
6 papers · 2023–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(18)
Top co-authors
Research topics
Keywords
large language model
(2)
certified robustness
(1)
image generation
(1)
data poisoning
(1)
fact verification
(1)
deepfake detection
(1)
out-of-distribution generalization
(1)
majority vote
(1)
false positive rate
(1)
adversarial attack
(1)
generative model
(1)
diffusion model
(1)
ensemble method
(1)
text-to-image model
(1)
tabular data
(1)
watermark detection
(1)
reasoning model
(1)
hallucination detection
(1)
membership inference
(1)
beam search
(1)
Papers
Reasoning’s Razor: Reasoning Improves Accuracy but Hurts Recall at Critical Operating Points in Safety and Hallucination Detection
EACL 2026
RePanda: Pandas-powered Tabular Verification and Reasoning
ACL 2025
Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models
ICLR 2025
Fast Adversarial Attacks on Language Models In One GPU Minute
ICML 2024
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
ICLR 2024
Run-off Election: Improved Provable Defense against Data Poisoning Attacks
ICML 2023