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 …
A survey of safety and trustworthiness of large language models through the lens of verification and validation
Large language models (LLMs) have exploded a new heatwave of AI for their ability to
engage end-users in human-level conversations with detailed and articulate answers across …
engage end-users in human-level conversations with detailed and articulate answers across …
Revisiting the assumption of latent separability for backdoor defenses
Recent studies revealed that deep learning is susceptible to backdoor poisoning attacks. An
adversary can embed a hidden backdoor into a model to manipulate its predictions by only …
adversary can embed a hidden backdoor into a model to manipulate its predictions by only …
Detecting backdoors in pre-trained encoders
Self-supervised learning in computer vision trains on unlabeled data, such as images or
(image, text) pairs, to obtain an image encoder that learns high-quality embeddings for input …
(image, text) pairs, to obtain an image encoder that learns high-quality embeddings for input …
A unified evaluation of textual backdoor learning: Frameworks and benchmarks
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 …
backdoor in the training phase, the adversary could control model predictions via predefined …
Backdoors against natural language processing: A review
Backdoors Against Natural Language Processing: A Review Page 1 50 September/October
2022 Copublished by the IEEE Computer and Reliability Societies 1540-7993/22©2022IEEE …
2022 Copublished by the IEEE Computer and Reliability Societies 1540-7993/22©2022IEEE …
Piccolo: Exposing complex backdoors in nlp transformer models
Backdoors can be injected to NLP models such that they misbehave when the trigger words
or sentences appear in an input sample. Detecting such backdoors given only a subject …
or sentences appear in an input sample. Detecting such backdoors given only a subject …
Notable: Transferable backdoor attacks against prompt-based nlp models
Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against
prompt-based models consider injecting backdoors into the entire embedding layers or word …
prompt-based models consider injecting backdoors into the entire embedding layers or word …
Plmmark: a secure and robust black-box watermarking framework for pre-trained language models
The huge training overhead, considerable commercial value, and various potential security
risks make it urgent to protect the intellectual property (IP) of Deep Neural Networks (DNNs) …
risks make it urgent to protect the intellectual property (IP) of Deep Neural Networks (DNNs) …
Towards practical deployment-stage backdoor attack on deep neural networks
One major goal of the AI security community is to securely and reliably produce and deploy
deep learning models for real-world applications. To this end, data poisoning based …
deep learning models for real-world applications. To this end, data poisoning based …