Deep learning models have achieved great success in solving a variety of natural language
processing (NLP) problems. An ever-growing body of research, however, illustrates the …

The massive spread of false information on social media has become a global risk, implicitly
influencing public opinion and threatening social/political development. False information …

Language Models (LMs) often cannot be deployed because of their potential to harm users
in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using …

Adversarial examples highlight model vulnerabilities and are useful for evaluation and
interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens …

The prevalence and strong capability of large language models (LLMs) present significant
safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive …

Multimodal contrastive learning aims to train a general-purpose feature extractor, such as
CLIP, on vast amounts of raw, unlabeled paired image-text data. This can greatly benefit …

Recently, the adversarial attack and defense technology has made remarkable
achievements and has been widely applied in the computer vision field, promoting its rapid …

The intriguing phenomenon of adversarial examples has attracted significant attention in
machine learning and what might be more surprising to the community is the existence of …

Deep Neural Network (DNN) classifiers are known to be vulnerable to Trojan or backdoor
attacks, where the classifier is manipulated such that it misclassifies any input containing an …

Facially manipulated images and videos or DeepFakes can be used maliciously to fuel
misinformation or defame individuals. Therefore, detecting DeepFakes is crucial to increase …