2 citations · 2 across the 7 of their papers we have counts for
7 papers
IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack
Yi Pan, Jun-Jie Huang, Tianrui Liu +3
Unrestricted adversarial transfer attacks are important for evaluating the black-box robustness of deep visual models. Diffusion-based attacks have shown promising transferability…
MissClick: Execution-Aware Adversarial Attacks on Coordinate Generation in GUI Grounding Models
Yu Ran, Wentao Zhao, Xin Zhang +1
Recent GUI visual grounding models generate screen coordinates as digit-token sequences that are parsed into numerical values and mapped to executable clicks. This generation-to-ex…
Combined Dictionary Unfolding Network with Gradient-Adaptive Fidelity for Transferable Multi-Source Fusion
Ge Luo, Jun-Jie Huang, Qi Yu +6
Deep Unfolding Network-based methods have emerged as effective solutions for multi-source image fusion by combining model-driven iterative optimization with data-driven deep learni…
SMILENet: Unleashing Extra-Large Capacity Image Steganography via a Synergistic Mosaic InvertibLE Hiding Network
Jun-Jie Huang, Zihan Chen, Tianrui Liu +5
Existing image steganography methods face fundamental limitations in hiding capacity (typically images) due to severe information interference and uncoordinated capacity-d…
SVASTIN: Sparse Video Adversarial Attack via Spatio-Temporal Invertible Neural Networks
Yi Pan, Jun-Jie Huang, Zihan Chen +2
Robust and imperceptible adversarial video attack is challenging due to the spatial and temporal characteristics of videos. The existing video adversarial attack methods mainly tak…
Invertible Mosaic Image Hiding Network for Very Large Capacity Image Steganography
Zihan Chen, Tianrui Liu, Jun-Jie Huang +3
The existing image steganography methods either sequentially conceal secret images or conceal a concatenation of multiple images. In such ways, the interference of information amon…
Imperceptible Adversarial Attack via Invertible Neural Networks
Zihan Chen, Ziyue Wang, Junjie Huang +3
Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples.…