Prompt Optimization and Evaluation for LLM Automated Red Teaming

Applications that use Large Language Models LLMs are becoming widespread, making the identification of system vulnerabilities increasingly important. Automated Red Teaming accelerates this effort by using an LLM to generate and execute attacks against target systems. Attack generators are evaluat...

CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks

Backdoor attacks have emerged as a critical security threat against deep neural networks in recent years. The majority of existing backdoor attacks focus on targeted backdoor attacks, where trigger is strongly associated to specific malicious behavior. Various backdoor detection methods depend on...