Đorđe Klisura
3 papers · 2025–2026 · 3 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 · Gold
🗺️
Taxonomy Completionist
(10)
Top co-authors
Research topics
Keywords
zero-shot learning
(1)
question answering
(1)
adversarial attack
(1)
language model
(1)
privacy leakage
(1)
refusal behavior
(1)
policy enforcement
(1)
privacy policy
(1)
zero-shot accuracy
(1)
multi-agent framework
(1)
access control
(1)
schema inference attack
(1)
zero-knowledge attack
(1)
database vulnerability
(1)
dialect bia
(1)
large language model
(1)
multi-agent system
(1)
database security
(1)
role-based policy
(1)
Papers
Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models
EACL 2026
A Multi-Agent Framework for Mitigating Dialect Biases in Privacy Policy Question-Answering Systems
ACL 2025
Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems
NAACL 2025