AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Consensus-Robust Transfer Attacks via Parameter and Representation Perturbations

Shixin Li, Zewei Li, Xiaojing Ma, Xiaofan Bai, Pingyi Hu, Dongmei Zhang, Bin Benjamin Zhu

NeurIPS 2025 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transferable adversarial examples · 0 citations (OpenAlex)

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.

Proposes a transfer attack for untargeted adversarial examples that frames transferability as consensus robustness, combining parameter and representation perturbations to handle decision-boundary variation and representation drift across models.

Problem

Adversarial examples crafted on one model often transfer poorly to other models in black-box settings, due to decision-boundary variation across models and representation drift in feature space.

Approach

Frames transferability of untargeted attacks as a consensus-robustness problem, perturbing model parameters and intermediate representations so that the adversarial example remains effective across the decision boundaries and feature representations of different models.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy