Structure invariant transformation for better adversarial transferability
Given the severe vulnerability of Deep Neural Networks (DNNs) against adversarial
examples, there is an urgent need for an effective adversarial attack to identify the …
examples, there is an urgent need for an effective adversarial attack to identify the …
Biasasker: Measuring the bias in conversational ai system
Powered by advanced Artificial Intelligence (AI) techniques, conversational AI systems, such
as ChatGPT, and digital assistants like Siri, have been widely deployed in daily life …
as ChatGPT, and digital assistants like Siri, have been widely deployed in daily life …
Boosting adversarial transferability by block shuffle and rotation
K Wang, X He, W Wang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Adversarial examples mislead deep neural networks with imperceptible perturbations and
have brought significant threats to deep learning. An important aspect is their transferability …
have brought significant threats to deep learning. An important aspect is their transferability …
Boosting adversarial transferability by achieving flat local maxima
Transfer-based attack adopts the adversarial examples generated on the surrogate model to
attack various models, making it applicable in the physical world and attracting increasing …
attack various models, making it applicable in the physical world and attracting increasing …
Rethinking the backward propagation for adversarial transferability
Transfer-based attacks generate adversarial examples on the surrogate model, which can
mislead other black-box models without access, making it promising to attack real-world …
mislead other black-box models without access, making it promising to attack real-world …
Improving the transferability of adversarial examples with arbitrary style transfer
Deep neural networks are vulnerable to adversarial examples crafted by applying human-
imperceptible perturbations on clean inputs. Although many attack methods can achieve …
imperceptible perturbations on clean inputs. Although many attack methods can achieve …
An image is worth a thousand toxic words: A metamorphic testing framework for content moderation software
The exponential growth of social media platforms has brought about a revolution in
communication and content dissemination in human society. Nevertheless, these platforms …
communication and content dissemination in human society. Nevertheless, these platforms …
On the robustness of latent diffusion models
Latent diffusion models achieve state-of-the-art performance on a variety of generative tasks,
such as image synthesis and image editing. However, the robustness of latent diffusion …
such as image synthesis and image editing. However, the robustness of latent diffusion …
[PDF][PDF] Towards Semantics-and Domain-Aware Adversarial Attacks.
Abstract Language models are known to be vulnerable to textual adversarial attacks, which
add humanimperceptible perturbations to the input to mislead DNNs. It is thus imperative to …
add humanimperceptible perturbations to the input to mislead DNNs. It is thus imperative to …
Validating multimedia content moderation software via semantic fusion
The exponential growth of social media platforms, such as Facebook, Instagram, Youtube,
and TikTok, has revolutionized communication and content publication in human society …
and TikTok, has revolutionized communication and content publication in human society …