How to Backdoor Large Language Models - Search Videos

Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks | Proceedings of the ACM on Management of Data

Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attacks | Proceedings of the ACM on Management of Data

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation | ACM Transactions on AI Security and Privacy

Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation | ACM Transactions on AI Security and Privacy

Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking | Proceedings of the 33rd ACM International Conference on Multimedia

Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking | Proceedings of the 33rd ACM International Conference on Multimedia

SoftPromptAttack: Advancing Backdoor Attacks in Language Models Through Prompt Learning Paradigms | Machine Learning for Cyber Security

SoftPromptAttack: Advancing Backdoor Attacks in Language Models Through Prompt Learning Paradigms | Machine Learning for Cyber Security

Backdoor Pre-trained Models Can Transfer to All | Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security

Backdoor Pre-trained Models Can Transfer to All | Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security

Transferable Dormant Backdoor: Covertly Embedding Transferable Backdoor via Knowledge Distillation in Pre-trained Models | Information Security and Cryptology

Transferable Dormant Backdoor: Covertly Embedding Transferable Backdoor via Knowledge Distillation in Pre-trained Models | Information Security and Cryptology

Going Back and Beyond: Emerging (Old) Threats in LLM Privacy and Poisoning

Going Back and Beyond: Emerging (Old) Threats in LLM Privacy and Poisoning

364 views5 months ago

YouTubeGoogle TechTalks

How Chatbots and Large Language Models Work

225.3K viewsAug 15, 2023

IMTM: Invisible Multi-trigger Multimodal Backdoor Attack | Natural Language Processing and Chinese Computing

Fine-Tuning vs RAG vs Prompt Engineering | LLM Optimization Methods Explained | #Shorts #Simplilearn

8.7K views6 days ago

YouTubeSimplilearn

What are Large Language Models (LLMs)?

372.5K viewsMay 5, 2023

YouTubeGoogle for Developers

Hello World: Meet Large Language Models | Amazon Web Services

16.5K viewsApr 13, 2023

YouTubeAmazon Web Services

B3: Backdoor Attacks against Black-box Machine Learning Models | ACM Transactions on Privacy and Security

Introduction to large language models

879.8K viewsMay 8, 2023

YouTubeGoogle Cloud Tech

Backdoor Two-Stream Video Models on Federated Learning | ACM Transactions on Multimedia Computing, Communications, and Applications

Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability | Proceedings of the ACM on Web Conference 2025

AI 101 for Teachers: Demystifying AI for Educators

41K viewsSep 22, 2023

AI models can acquire backdoors from surprisingly few malicious documents

arstechnica.com

See more