arXiv Machine Learning June 9, 2026 By Xin Li, Chenhan Xiao, Jonathan Cohen, Aviad Elyashar, Yang Weng, Rami Puzis

Physically Consistent Null Space Alignment for Detection of Low-Magnitude False Data Injection Attacks

Read the original on arXiv Machine Learning →

arXiv:2606. 08473v1 Announce Type: new Abstract: False data injection attacks (FDIAs) introducing small measurement perturbations can still cause large deviations in power system state estimation when the injected signals align with the pseudo-null space of the system model.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

safety

arXiv Machine Learning

Jun 9

Cycle-Space Informed Detection of Autoencoded Blind False Data Injection Attacks on Power Systems

arXiv:2605. 28912v2 Announce Type: replace Abstract: The rapid growth of AI-driven data centers and large-scale energy storage systems is increasing the reliance of power system operation on real-time measurement data and automated decision-making.

By Xin Li, Chenhan Xiao, Jonathan Cohen, Aviad Elyashar, Yang Weng, Rami Puzis

arXiv Machine Learning

Jun 19

Pseudo-Feature Padding: A Lightweight Defense Against False Data Injection in Power Grids

arXiv:2606.

By Farhin Farhad Riya, Shahinul Hoque, Yingyuan Yang, Jinyuan Sun, Kevin Tomsovic

safety

arXiv Machine Learning

Jun 5

Attack Detection using Time Series Foundation Models

arXiv:2606. 06347v1 Announce Type: cross Abstract: This paper addresses the problem of attack detection in cyber-physical systems without any knowledge of the plant model or its structure.

By Sribalaji C. Anand, Anh Tung Nguyen, George J. Pappas

arXiv Machine Learning

Jul 9

ORAN-DEFEND: Subspace Detection and Sanitization of Backdoor DRL xApps in Open RAN

arXiv:2607. 06647v1 Announce Type: cross Abstract: Open Radio Access Networks (O-RAN) increasingly delegate near-real-time control to deep reinforcement learning (DRL) xApps obtained from third-party vendors, creating a new supply-chain attack surface.

By Md Raihan Uddin, Fatemeh Lotfi, Tolunay Seyfi, Fatemeh Afghah

reinforcement-learning benchmarks

arXiv AI

Jul 20

Revisiting data-driven dynamic security assessment with a tabular foundation model

arXiv:2607. 16031v1 Announce Type: cross Abstract: Data-driven pre-fault dynamic security assessment (DSA) rapidly evaluates the dynamic risk of credible contingencies on a power system using machine learning.

By Olayiwola Arowolo, Maosheng Yang, Jochen Cremer

llms fine-tuning

arXiv AI

Jun 16

InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Reset

arXiv:2606. 15730v1 Announce Type: cross Abstract: Backdoor unlearning aims to remove a malicious trigger behavior from a deployed model while preserving clean utility.

By Zhenyu Yu

multimodal

Related stories

Cycle-Space Informed Detection of Autoencoded Blind False Data Injection Attacks on Power Systems

Pseudo-Feature Padding: A Lightweight Defense Against False Data Injection in Power Grids

Attack Detection using Time Series Foundation Models

ORAN-DEFEND: Subspace Detection and Sanitization of Backdoor DRL xApps in Open RAN

Revisiting data-driven dynamic security assessment with a tabular foundation model

InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Reset