Picture for Tianyu Du

Tianyu Du

CopyrightMeter: Revisiting Copyright Protection in Text-to-image Models

Add code
Nov 20, 2024
Viaarxiv icon

HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models

Add code
Oct 30, 2024
Viaarxiv icon

CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment

Add code
Oct 16, 2024
Viaarxiv icon

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

Add code
Oct 12, 2024
Viaarxiv icon

Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding

Add code
Oct 02, 2024
Figure 1 for Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
Figure 2 for Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
Figure 3 for Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
Figure 4 for Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding
Viaarxiv icon

CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models

Add code
Sep 02, 2024
Figure 1 for CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
Figure 2 for CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
Figure 3 for CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
Figure 4 for CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
Viaarxiv icon

LABOR-LLM: Language-Based Occupational Representations with Large Language Models

Add code
Jun 25, 2024
Viaarxiv icon

MemDPT: Differential Privacy for Memory Efficient Language Models

Add code
Jun 16, 2024
Figure 1 for MemDPT: Differential Privacy for Memory Efficient Language Models
Figure 2 for MemDPT: Differential Privacy for Memory Efficient Language Models
Figure 3 for MemDPT: Differential Privacy for Memory Efficient Language Models
Figure 4 for MemDPT: Differential Privacy for Memory Efficient Language Models
Viaarxiv icon

Tool-Planner: Dynamic Solution Tree Planning for Large Language Model with Tool Clustering

Add code
Jun 06, 2024
Viaarxiv icon

Could It Be Generated? Towards Practical Analysis of Memorization in Text-To-Image Diffusion Models

Add code
May 09, 2024
Viaarxiv icon