3 accepted papers
Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic or implicit triggers. This increased flexibility in trigger
Large language models (LLMs) exhibit exceptional performance across a wide range of natural language processing tasks, often relying on lengthy prompts to harness their full capabilities. However, extended prompts can lead to substantial computational overhead and increased hardware demands, limitin…
The design of effective online caching policies is an increasingly important problem for content distribution networks, online recommender systems, and edge computing services, etc. Exiting literature usually tackles this problem through the lens of optimistic online learning and aims to achieve sub…