ZeroHour

Search: “visualization”

3,847 stories

Unmasking Cloud Identities: From Behavioral Clustering to Automated Detection

Unit 42 clusters behavior of 40,000+ AWS identities from 125 cloud environments to map functional roles and enable lightweight SQL-based detection.

Palo Alto Unit 42 built an unsupervised behavioral clustering model using UMAP and HDBSCAN on AWS CloudTrail logs to map cloud identities to functional roles such as administrators, backup services, security tooling and DevOps. The study analyzed over 40,000 identities across 125 cloud environments over two months. The researchers show that heuristics extracted from the clustering map can be implemented in standard SQL, enabling role classification at scale without running a continuous ML pipeline. The methodology extends to audit logs from other cloud providers, SaaS and Kubernetes.

Palo Alto Unit 42 · 1d agoResearch

Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded Supervision

ECCV 2026 challenge winner reformulates egocentric intervention timing as single-token classification, boosting macro-F1 by 0.249 over free-form generation.

The paper describes the winning submission to the EgoProactive track of the ECCV 2026 Wearable AI Challenge, ranking first in the large-model division and second in the <=2B division. The method reformulates intervention timing as single-token yes/no classification, improving macro-F1 by 0.249 and G-mean by 0.30 over free-form generation. Supervision generated by a tool-calling video agent transferred better than a narration-only dataset that was four times larger and ten times cheaper, suggesting visual grounding matters more than annotation volume.

Hugging Face daily papers · 6d agoAI research

Microsoft September 2026 Patch Tuesday fixes 966 flaws, 2 zero-days

Microsoft's September 2026 Patch Tuesday fixes a record 966 flaws, including two Windows zero-days actively exploited to gain SYSTEM privileges.

Microsoft's September 2026 Patch Tuesday addresses a record 966 vulnerabilities, including 105 rated Critical, 81 of them remote code execution bugs. Two zero-days were actively exploited: a Windows Update Stack link-following flaw and a Windows ALPC heap-based buffer overflow, both allowing local elevation to SYSTEM privileges. The ALPC flaw was reported by Volexity and Proofpoint researchers, while the Update Stack flaw was credited to Romain Deperne and the Microsoft Threat Intelligence Centre. Microsoft shared no details on how the flaws were exploited in attacks.

BleepingComputer · 7d agoAdvisory in the wildCVE-2026-69805CVE-2026-58649CVE-2026-69806+27 CVEs1

VoT: Vision-of-Thought for Unified Multimodal Representation Alignment

Researchers propose Vision-of-Thought (VoT), a discrete visual-planning token layer between VLMs and diffusion transformers improving text-to-image semantic alignment.

VoT introduces a discrete visual-thinking layer between vision-language models and diffusion transformers, letting the VLM act as a multimodal planner that emits tokens describing objects and layouts before pixel generation. A specialized VoT tokenizer is trained with VLM alignment, feature reconstruction, and vector-quantization losses. Experiments show improved semantic alignment and a structured, interpretable interface for controllable generation.

arXiv cs.AI / cs.LG / cs.CL · 8d agoAI research

Training-Free Speech-Centric Omni Understanding with Frozen VLMs

Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and their temporal relationships. Existing omni models typically introduce dedicated audio encoders and rely on expensive audio-video-text training, tightly coupling omni capability to specific VLM backbones and potentially weakening their existing visual and reasoning abilities.…

Hugging Face daily papers · Aug 6, 2026AI research