Prompt Injection, 2022 vs Today: A Retrospective
Published:
Posts by Tags
Adversarial Fine-Tuning
Code Assistants
Does AI Make You Write Insecure Code? A User Study
Published:
Does AI Make You Write Insecure Code? A User Study
Deep Learning
Adversarial Fineturning against Prompt Injection Attacks
Published:
🛡️ Securing Large Language Models: Adversarial Fine-Tuning Against Prompt Injection
LLM
Mechanistic Interpretability as a Security Tool
Published:
Mechanistic Interpretability as a Security Tool
Prompt Injection, 2022 vs Today: A Retrospective
Published:
Prompt Injection, 2022 vs Today: A Retrospective
The Format-Reliability Gap: Diagnosing and Repairing Insecure Code Generation
Published:
The Format-Reliability Gap: Diagnosing and Repairing Insecure Code Generation
Does AI Make You Write Insecure Code? A User Study
Published:
Does AI Make You Write Insecure Code? A User Study
Adversarial Fineturning against Prompt Injection Attacks
Published:
🛡️ Securing Large Language Models: Adversarial Fine-Tuning Against Prompt Injection
Mechanistic Interpretability
Mechanistic Interpretability as a Security Tool
Published:
Mechanistic Interpretability as a Security Tool
The Format-Reliability Gap: Diagnosing and Repairing Insecure Code Generation
Published:
The Format-Reliability Gap: Diagnosing and Repairing Insecure Code Generation
Prompt Injection
Prompt Injection, 2022 vs Today: A Retrospective
Published:
Prompt Injection, 2022 vs Today: A Retrospective
Secure Code Generation
The Format-Reliability Gap: Diagnosing and Repairing Insecure Code Generation
Published:
The Format-Reliability Gap: Diagnosing and Repairing Insecure Code Generation
Security
Mechanistic Interpretability as a Security Tool
Published:
Mechanistic Interpretability as a Security Tool
Prompt Injection, 2022 vs Today: A Retrospective
Published:
Prompt Injection, 2022 vs Today: A Retrospective
The Format-Reliability Gap: Diagnosing and Repairing Insecure Code Generation
Published:
The Format-Reliability Gap: Diagnosing and Repairing Insecure Code Generation
Does AI Make You Write Insecure Code? A User Study
Published:
Does AI Make You Write Insecure Code? A User Study
Adversarial Fineturning against Prompt Injection Attacks
Published:
🛡️ Securing Large Language Models: Adversarial Fine-Tuning Against Prompt Injection
Steering
Mechanistic Interpretability as a Security Tool
Published:
Mechanistic Interpretability as a Security Tool
User Study
Does AI Make You Write Insecure Code? A User Study
Published: