Research map / Adversarial robustness and security / Attacks on text and graphs
Resolution Attack: Exploiting Image Compression to Deceive Deep Neural Networks
Wangjia Yu, Xiaomeng Fu, Qiao Li, Jizhong Han, Xiaodan Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Introduces the resolution attack, which exploits image compression/resolution changes to deceive deep neural networks, probing model robustness to different input resolutions.
Problem
Model robustness to different image resolutions has been little explored compared with adversarial robustness and label-noise robustness.
Approach
A new attack form that manipulates image resolution (via compression) so that deep neural networks are deceived, treating resolution shifts as an attack surface for model robustness evaluation.
Closest papers by meaning
- Evaluating Robustness of Deep Image Super-Resolution Against Adversarial Attacks (ICCV 2019 · similarity 0.87)
- Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models (CVPR 2024 · similarity 0.86)
- Variance as a Catalyst: Efficient and Transferable Semantic Erasure Adversarial Attack for Customized Diffusion Models (ICML 2025 · similarity 0.85)
- IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks (ICLR 2024 · similarity 0.85)
- High-Fidelity Gradient Inversion in Distributed Learning (AAAI 2024 · similarity 0.85)
- DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
