Prompt Injection Attacks in Defended Systems
Evaluating the effectiveness of prompt injection attacks against LLMs with defensive mechanisms.
🛡️ AI Safety & LLM Security
Investigating LLM-as-a-Judge Vulnerability to Prompt Injection
Security analysis of LLM-based evaluation systems and their susceptibility to adversarial manipulation.
Adversarial Attacks on LLM-as-a-Judge Systems
Comprehensive study of prompt injection techniques targeting automated LLM evaluation pipelines.
Trojan Detection in Large Language Models
Insights from the Trojan Detection Challenge on identifying backdoors in language models.
📝 NLP & Text Analysis
DIALOG-22 RuATD: Generated Text Detection
Detecting AI-generated text in Russian language using machine learning classifiers.
Low-Resource Language Text Classification
Fine-tuning multilingual pretrained models for African language sentiment analysis.
🏥 Medical AI & Computer Vision
Noninvasive Glioma Grading with Deep Learning
Deep learning approach for non-invasive brain tumor classification from MRI scans.
MR-guided Non-invasive Brain Glioma Typing
Machine learning for MRI-based glioma classification in clinical neurosurgery settings.
Neurosurgical Instrument Segmentation
Computer vision for tracking surgical instruments to assess microsurgical skill.
Blind Face Restoration Survey
Comprehensive survey of deep learning methods for restoring degraded face images.
🔧 Robotics
Synthesis of L-coordinate Parallel Mechanism
Design of singularity-free parallel robotic mechanisms for precise positioning.