Pre-trained language models (PTLMs) have achieved great success and remarkable
performance over a wide range of natural language processing (NLP) tasks. However, there …

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 …

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 …

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 …

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 …

Modern language models are vulnerable to backdoor attacks. An injected malicious token
sequence (ie, a trigger) can cause the compromised model to misbehave, raising security …

Modern autonomous vehicles adopt state-of-the-art DNN models to interpret the sensor data
and perceive the environment. However, DNN models are vulnerable to different types of …

Deep learning is becoming increasingly popular in real-life applications, especially in
natural language processing (NLP). Users often choose training outsourcing or adopt third …

With the rapid development of deep learning, training Big Models (BMs) for multiple
downstream tasks becomes a popular paradigm. Researchers have achieved various …

Class incremental learning from a pre-trained DNN model is gaining lots of popularity.
Unfortunately, the pre-trained model also introduces a new attack vector, which enables an …