Abstract Generative Pre-trained Transformer (GPT) models have exhibited exciting progress
in their capabilities, capturing the interest of practitioners and the public alike. Yet, while the …

Since the emergence of security concerns in artificial intelligence (AI), there has been
significant attention devoted to the examination of backdoor attacks. Attackers can utilize …

Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so
that the attacked models perform well on benign samples, whereas their predictions will be …

With the rapid development of artificial intelligence, large language models (LLMs) have
made remarkable advancements in natural language processing. These models are trained …

We investigate security concerns of the emergent instruction tuning paradigm, that models
are trained on crowdsourced datasets with task instructions to achieve superior …

The advancement of large language models (LLMs) has significantly enhanced the ability to
effectively tackle various downstream NLP tasks and unify these tasks into generative …

The vulnerability of deep neural networks (DNN) to backdoor (trojan) attacks is extensively
studied for the image domain. In a backdoor attack, a DNN is modified to exhibit expected …

Shortcut Learning of Large Language Models in Natural Language Understanding Page 1 110
COMMUNICATIONS OF THE ACM | JANUARY 2024 | VOL. 67 | NO. 1 research IMA GE B Y …

The prompt-based learning paradigm has gained much research attention recently. It has
achieved state-of-the-art performance on several NLP tasks, especially in the few-shot …

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a
backdoor in the training phase, the adversary could control model predictions via predefined …