Structure invariant transformation for better adversarial transferability

X Wang, Z Zhang, J Zhang - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
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 …

Biasasker: Measuring the bias in conversational ai system

Y Wan, W Wang, P He, J Gu, H Bai… - Proceedings of the 31st …, 2023 - dl.acm.org
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 …

Boosting transferability in vision-language attacks via diversification along the intersection region of adversarial trajectory

S Gao, X Jia, X Ren, I Tsang, Q Guo - European Conference on Computer …, 2024 - Springer
Vision-language pre-training (VLP) models exhibit remarkable capabilities in
comprehending both images and text, yet they remain susceptible to multimodal adversarial …

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 …

Boosting adversarial transferability by achieving flat local maxima

Z Ge, H Liu, W **aosen, F Shang… - Advances in Neural …, 2023 - proceedings.neurips.cc
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 …

Rethinking the backward propagation for adversarial transferability

W **aosen, K Tong, K He - Advances in Neural Information …, 2023 - proceedings.neurips.cc
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 …

Improving the transferability of adversarial examples with arbitrary style transfer

Z Ge, F Shang, H Liu, Y Liu, L Wan, W Feng… - Proceedings of the 31st …, 2023 - dl.acm.org
Deep neural networks are vulnerable to adversarial examples crafted by applying human-
imperceptible perturbations on clean inputs. Although many attack methods can achieve …

Typography leads semantic diversifying: Amplifying adversarial transferability across multimodal large language models

H Cheng, E **ao, J Yang, J Cao, Q Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
Recently, Multimodal Large Language Models (MLLMs) achieve remarkable performance in
numerous zero-shot tasks due to their outstanding cross-modal interaction and …

Resilience and security of deep neural networks against intentional and unintentional perturbations: Survey and research challenges

S Sayyed, M Zhang, S Rifat, A Swami… - arxiv preprint arxiv …, 2024 - arxiv.org
In order to deploy deep neural networks (DNNs) in high-stakes scenarios, it is imperative
that DNNs provide inference robust to external perturbations-both intentional and …

Enhancing transferability of adversarial examples through mixed-frequency inputs

Y Qian, K Chen, B Wang, Z Gu, S Ji… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Recent studies have shown that Deep Neural Networks (DNNs) are easily deceived by
adversarial examples, revealing their serious vulnerability. Due to the transferability …