arXiv:2608. 16334v1 Announce Type: new Abstract: Keystroke dynamics (typing patterns) can be used as a behavioural biometric modality for user authentication, with applications such as fraud prevention.
By Nuwan Kaluarachchi, Sevvandi Kandanaarachchi, Kristen Moore, Arathi Arakala, Conrad Sanderson
arXiv:2609.22724v1 Announce Type: cross
Abstract: Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices, but their trajectories can violate app-specifi...
By Changyue Jiang, Jiayi Wang, Xin Wen, Jiarun Dai, Geng Hong, Xudong Pan
MobileWorldSafety is a benchmark that evaluates the safety of large language model–powered GUI agents on Android by exposing them to 142 real-world risk tasks involving environmental injection attacks. The benchmark uses a two‑stage verification pipeline—rule‑based checks for clear cases and an LLM judge for ambiguous ones—to distinguish safety failures from capability failures. Experiments on six agents show high vulnerability, with attack success rates between 40.4% and 66.9%, highlighting that current agents often fail to remain safe when faced with adversarial content presented as normal mobile context.
By Sujin Chen, Lijun Li, Tianyi Du, Jing Shao
arXiv:2605. 09028v3 Announce Type: replace Abstract: Machine learning-based Android malware detectors often fail in real-world deployment due to domain shift, where models trained on one data source perform poorly on applications from another.
By Md Rafid Islam
arXiv:2607. 11649v1 Announce Type: cross Abstract: Network-based anomaly detection for IoT devices has matured to the point of reporting strong detection accuracy, yet most published systems stop at raising an alert and leave the question of automated enforcement to future work or to a programmable data plane that few real networks operate.
By Muhammet Emir Korkmaz, Kemal Bicakci, Yusuf Uzunay
RouteScan is a non‑intrusive auditing framework that detects harmful behavior in Mixture‑of‑Experts (MoE) large language models by analyzing expert‑routing telemetry captured from GPU execution. It uses the number of active GPU threads during the prefilling phase as a micro‑architectural fingerprint to isolate cross‑domain risk indicators and precisely identify malicious prompts. Evaluations on four open‑source MoE LLMs show strong generalization with AUROC > 0.91 on unseen harmful domains, while privacy tests indicate that full prompts cannot be reliably recovered from aggregated telemetry.
By Bo Lv, Zhiheng Xu, KeDong Xiu, Ruyi Ding, Tianhang Zheng, Zhibo Wang, Kui Ren