Backdoor pre-trained models can transfer to all
Pre-trained general-purpose language models have been a dominating component in
enabling real-world natural language processing (NLP) applications. However, a pre-trained …
enabling real-world natural language processing (NLP) applications. However, a pre-trained …
Badpre: Task-agnostic backdoor attacks to pre-trained nlp foundation models
Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety
of downstream language tasks. This significantly accelerates the development of language …
of downstream language tasks. This significantly accelerates the development of language …
Moderate-fitting as a natural backdoor defender for pre-trained language models
Despite the great success of pre-trained language models (PLMs) in a large set of natural
language processing (NLP) tasks, there has been a growing concern about their security in …
language processing (NLP) tasks, there has been a growing concern about their security in …
Setting the trap: Capturing and defeating backdoors in pretrained language models through honeypots
In the field of natural language processing, the prevalent approach involves fine-tuning
pretrained language models (PLMs) using local samples. Recent research has exposed the …
pretrained language models (PLMs) using local samples. Recent research has exposed the …
Training-free lexical backdoor attacks on language models
Large-scale language models have achieved tremendous success across various natural
language processing (NLP) applications. Nevertheless, language models are vulnerable to …
language processing (NLP) applications. Nevertheless, language models are vulnerable to …
Rethinking stealthiness of backdoor attack against nlp models
Recent researches have shown that large natural language processing (NLP) models are
vulnerable to a kind of security threat called the Backdoor Attack. Backdoor attacked models …
vulnerable to a kind of security threat called the Backdoor Attack. Backdoor attacked models …
Turn the combination lock: Learnable textual backdoor attacks via word substitution
Recent studies show that neural natural language processing (NLP) models are vulnerable
to backdoor attacks. Injected with backdoors, models perform normally on benign examples …
to backdoor attacks. Injected with backdoors, models perform normally on benign examples …
Hidden backdoors in human-centric language models
Natural language processing (NLP) systems have been proven to be vulnerable to backdoor
attacks, whereby hidden features (backdoors) are trained into a language model and may …
attacks, whereby hidden features (backdoors) are trained into a language model and may …
Threats to pre-trained language models: Survey and taxonomy
Pre-trained language models (PTLMs) have achieved great success and remarkable
performance over a wide range of natural language processing (NLP) tasks. However, there …
performance over a wide range of natural language processing (NLP) tasks. However, there …
Badchain: Backdoor chain-of-thought prompting for large language models
Large language models (LLMs) are shown to benefit from chain-of-thought (COT) prompting,
particularly when tackling tasks that require systematic reasoning processes. On the other …
particularly when tackling tasks that require systematic reasoning processes. On the other …