Implementing a White-Box Undetectable Backdoor for Random Fourier Features

arXiv:2609.16403 · cs.CR, cs.LG · Submitted 2026-09-14 · Read on arXiv

cs.CR, cs.LG

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 13 pages, 4 figures, 4 tables

Code: https://github.com/rossgore/weird_machine_gadgets

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Random Fourier Features — 19× in this paper
• Sparsity — 15× in this paper · explained in 4 episodes
• Learning With Errors — 8× in this paper
• Core — 7× in this paper · explained in 2 episodes
• Ambient Dimension — 3× in this paper · explained in 1 episode
• Continuous Learning With Errors — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Spectral Signature — 2× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adversarial Attacks — 1× in this paper · explained in 1 episode
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Adversarial Robustness — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Differential Privacy — 1× in this paper · explained in 4 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• SIGACT Symposium on Theory of Computing — 1× in this paper
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Continuous LWE is as Hard as LWE & Applications to Learning Gaussian Mixtures
• BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• Black-box Detection of Backdoor Attacks with Limited Information and Data
• Computational Lower Bounds for Sparse PCA

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs