Sahar Abdelnabi
8 papers · 2021–2026 · 7 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 ↓+3 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (27) 🌍 Conference Polyglot · Silver
👥
Mega-Team · Squad
❓
The Questioner
🗃️
Keyword Collector
(53)
Top co-authors
Research topics
Artificial Intelligence
(7)
Core AI · Artificial Intelligence
(7)
Deep Learning
(4)
Machine Learning
(3)
Computer Vision
(2)
Analysis
(2)
Application Areas
(2)
Learning Types · Deep Learning
(2)
Models
(2)
Knowledge & Reasoning
(1)
Natural Language Processing
(1)
Applications
(1)
Core AI · Computer Vision
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Keywords
large language model
(3)
multi-agent system
(2)
prompt injection
(2)
image generation
(1)
game theory
(1)
visual question answering
(1)
interactive negotiation
(1)
visual reasoning
(1)
deepfake detection
(1)
ai safety
(1)
observational study
(1)
adversarial attack
(1)
language model
(1)
generative adversarial network
(1)
security evaluation
(1)
bias analysis
(1)
model utility
(1)
visual evidence
(1)
multi-agent setup
(1)
multimodal learning
(1)
Papers
ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations
EACL 2026
A Theory of Response Sampling in LLMs: Part Descriptive and Part Prescriptive
ACL 2025
Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
ICLR 2025
Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables
EMNLP 2025
Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
NeurIPS 2024
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
NeurIPS 2024
Open-Domain, Content-Based, Multi-Modal Fact-Checking of Out-of-Context Images via Online Resources
CVPR 2022
Artificial Fingerprinting for Generative Models: Rooting Deepfake Attribution in Training Data
ICCV 2021