Research map / Adversarial robustness and security / Black-box and transfer attacks
Adversarial Attack and Defense for Machine Learning in Statistical Physics
Zhao-Rong Lai, Qiantong Liang, Jian Weng
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.
Studies adversarial attacks and defenses for machine learning systems used in statistical physics, highlighting their vulnerability to noise and perturbations outside ideal settings.
Problem
ML systems proposed for physical science are evaluated in ideal environments that ignore noise, perturbations, and real-world experimental limitations, leaving them vulnerable.
Approach
Applies adversarial attack and defense analysis to ML models for statistical physics, examining their robustness to perturbations that the original ideal-environment evaluations ignore.
Closest papers by meaning
- Susceptibilities for Neural Networks Learning from Physical Data (NeurIPS 2026 · similarity 0.87)
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models (ICLR 2018 · similarity 0.86)
- Adversarial Robustness via Deformable Convolution with Stochasticity (ICML 2025 · similarity 0.85)
- Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks (ICLR 2024 · similarity 0.85)
- Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature (AAAI 2025 · similarity 0.84)
- Strong Transferable Adversarial Attacks via Ensembled Asymptotically Normal Distribution Learning (CVPR 2024 · 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.
