Textual backdoor attacks pose a practical threat to existing systems, as they can
compromise the model by inserting imperceptible triggers into inputs and manipulating …

Recently, various parameter-efficient fine-tuning (PEFT) strategies for application to
language models have been proposed and successfully implemented. However, this raises …

Deep Neural Networks (DNNs) have led to unprecedented progress in various natural
language processing (NLP) tasks. Owing to limited data and computation resources, using …

The security of multi-turn conversational large language models (LLMs) is understudied
despite it being one of the most popular LLM utilization. Specifically, LLMs are vulnerable to …

This tutorial seeks to provide a systematic summary of risks and vulnerabilities in security,
privacy and copyright aspects of large language models (LLMs), and most recent solutions …

Transformers have advanced the state-of-the-art on a variety of natural language processing
tasks [255, 70] and see increasing popularity in the field of computer vision [74, 157]. The …