arXiv AI August 17, 2026 By Steven Lamp, Jason D. Hiser, Anh Nguyen-Tuong, Jack W. Davidson

PHASE: Passive Human Activity Simulation Evaluation

arXiv:2507. 13505v2 Announce Type: replace-cross Abstract: Cybersecurity simulation environments, such as cyber ranges, honeypots, and sandboxes, require realistic human behavior to be effective, yet no quantitative method exists to assess the behavioral fidelity of synthetic user personas.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 17

Multi-Source Cybersecurity Logs: An ATT&CK-Labeled Dataset and SLM Evaluation

arXiv:2606. 18190v1 Announce Type: cross Abstract: Multi-stage cyberattacks span system, network, and browser logs.

By Abir Ashab Niloy, Ahmed Ryan, Imamul Hossain Rafi, Md Erfan, Md Rayhanur Rahman

llms fine-tuning safety

arXiv AI

Aug 17

Interactive Analysis of Global Explanations using Aggregated Class Activation Maps for Network Data

arXiv:2608. 13575v1 Announce Type: cross Abstract: Recent machine learning (ML) advances have demonstrated that deep learning (DL) achieves impressive results in different application domains, including the classification of computer network traffic to corresponding applications.

By Igor Cherepanov, David Sessler, Alex Ulmer, Felix Wagner, Throsten May, J\"orn Kohlhammer

arXiv AI

3d ago

SimTrace: Grounded Multimodal User Trajectories Generation for Online User Modeling

arXiv:2609.38397v1 Announce Type: new Abstract: Virtual clients offer a cost-effective approach to support applications such as A/B testing, recommender system development, and interface evaluation....

By Yunan Lu, Shuang Xie, Meghna Allamudi, Mingyu Zhao, Han Li, Lingyun Wang, Zhou Yu

agents multimodal safety

arXiv Machine Learning

Jul 1

Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale

arXiv:2606. 30801v1 Announce Type: cross Abstract: Personalization algorithms determine what content users encounter on online platforms.

By Alessandro Morosini, Sarah H. Cen, Andrew Ilyas, Hedi Driss, Aleksander M\k{a}dry, Chara Podimata

agents

arXiv AI

Sep 2

Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations

arXiv:2609.01257v1 Announce Type: new Abstract: As LLM-based human simulators are increasingly used for policy, evaluation, and training, they must faithfully reproduce real behavioral patterns. Whil...

By Yi Fei Cheng, Fan Yang, Iremsu Bas, Koichiro Niinuma, Narishige Abe, David Lindlbauer

llms

arXiv Machine Learning

Jun 15

Dynamic Free-Rider Detection in Federated Learning via Simulated Attack Patterns

arXiv:2604. 04611v2 Announce Type: replace Abstract: Federated learning (FL) enables multiple clients to collaboratively train a global model by aggregating local updates without sharing private data.

By Motoki Nakamura

One email a morning, machine-written

Related stories

Multi-Source Cybersecurity Logs: An ATT&CK-Labeled Dataset and SLM Evaluation

Interactive Analysis of Global Explanations using Aggregated Class Activation Maps for Network Data

SimTrace: Grounded Multimodal User Trajectories Generation for Online User Modeling

Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale

Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations

Dynamic Free-Rider Detection in Federated Learning via Simulated Attack Patterns