LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked

Meta Large Language Model Compiler: Foundation Models of Compiler Optimization

Unlearning Bias in Language Models by Partitioning Gradients

ProPILE: Probing Privacy Leakage in Large Language Models

Improving Real-world Password Guessing Attacks via Bi-directional Transformers

Semantic Ranking for Automated Adversarial Technique Annotation in Security Text

LogBERT: Log Anomaly Detection via BERT

Universal and Transferable Adversarial Attacks on Aligned Language Models

Membership Inference via Backdooring

Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations