Privacy-Aware Synthetic Video Benchmarking and Relational Evaluation for Worker-Under-Suspended-Load Detection

• URL: http://arxiv.org/abs/2607.16351v1
• Date: Fri, 17 Jul 2026 06:20:20 GMT
• Title: Privacy-Aware Synthetic Video Benchmarking and Relational Evaluation for Worker-Under-Suspended-Load Detection
• Abstract summary: We introduce SynthSite, a focused synthetic video benchmark of 55 clips spanning varied load configurations, viewpoints, clutter, and surveillance conditions.<n>We ask whether worker appearance can be suppressed without undermining downstream hazard recognition.<n>We find that structure-hugging obfuscations retain substantially more downstream utility than appearance-smoothing baselines.
• Score: 46.13517417540154
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Publicly shareable construction-video benchmarks remain scarce, especially for safety-critical hazards that are rare, dangerous to stage, and difficult to release. We study worker under suspended load, a relational hazard that depends on worker-load geometry and temporal persistence rather than object detection alone. We introduce SynthSite, a focused synthetic video benchmark of 55 clips spanning varied load configurations, viewpoints, clutter, occlusions, and surveillance conditions, together with a privacy-aware hybrid generation workflow that supports both publicly shareable benchmark creation and privacy-constrained synthetic video generation. We then ask whether worker appearance can be suppressed without undermining downstream hazard recognition. Under five whole-body privacy conditions, we evaluate worker and load retention, localization stability, and clip-level hazard recognition. We find that structure-preserving obfuscations retain substantially more downstream utility than appearance-smoothing baselines, and that preserving a raw visual reference alone does not guarantee the strongest agreement with human hazard labels. These findings suggest that privacy evaluation for construction safety analytics should assess not only appearance suppression, but also preservation of the geometric cues required for hazard reasoning. Our dataset and code are available at https://huggingface.co/datasets/govtech/SynthSite .

Related papers

• Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface [1.3037017215576172]
  Federated learning enables privacy-conscious collaboration for network intrusion detection without centralizing sensitive traffic data.<n>It must simultaneously satisfy three competing requirements: formal differential privacy guaranties, tolerance to Byzantine-adversarial participants, and reliable detection coverage across severely imbalanced attack categories.<n>We study how these requirements interact in class-imbalanced NIDS and introduce geometric indistinguishability as a conceptual lens for a regime in which privacy-induced dispersion in client updates can make minority-class signals harder for robust aggregation to preserve.
  arXiv  Detail & Related papers  (2026-09-03T06:27:03Z)
• Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle [65.6642776933861]
  This survey examines the protective paradigm that has grown around this intervention point.<n>We find that most protections are still validated mainly against static or weakly adaptive adversaries.<n>We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.
  arXiv  Detail & Related papers  (2026-08-05T00:46:50Z)
• Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOMPBENCH [21.171990974350773]
  DeCompBench is a benchmark designed to evaluate agentic safety under decomposition attacks.<n>Our experiments show that state-of-the-art agents exhibit high refusal rates on monolithic harmful tasks, but significantly lower refusal rates on their variants.
  arXiv  Detail & Related papers  (2026-06-12T00:30:29Z)
• What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media [14.75272852371927]
  Public social media posts can reveal private information through weak cues scattered across text, images, or metadata.<n>We propose SopriBench, a synthetic benchmark guided by leakage patterns abstracted from a private reference corpus of Rednote and Instagram accounts.<n>Inspired by abductive reasoning, we introduce Argus, a training-free agentic framework for cumulative leakage inference.
  arXiv  Detail & Related papers  (2026-06-05T00:02:47Z)
• Rethinking Visual Privacy: A Compositional Privacy Risk Framework for Severity Assessment with VLMs [58.7856837806126]
  Existing visual privacy benchmarks largely treat privacy as a binary property, labeling images as private or non-private based on visible sensitive content.<n>We argue that privacy is fundamentally compositional. Attributes that are benign in isolation may combine to produce severe privacy violations.<n>We introduce the Compositional Privacy Risk Taxonomy (CPRT), a regulation-aware framework that organizes visual attributes according to standalone identifiability and compositional harm potential.
  arXiv  Detail & Related papers  (2026-03-23T04:48:42Z)
• HomeGuard: VLM-based Embodied Safeguard for Identifying Contextual Risk in Household Task [42.665798473119516]
  We propose an architecture-agnostic safeguard featuring Context-Guided Chain-of-Thought (CG-CoT)<n>CG-CoT decomposes risk assessment into active perception that sequentially anchors attention to interaction targets and relevant spatial neighborhoods.<n> Experiments demonstrate that our model HomeGuard significantly enhances safety, improving risk match rates by over 30% compared to base models.
  arXiv  Detail & Related papers  (2026-03-15T13:09:43Z)
• Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation [50.87199039334856]
  Retrieval-Augmented Generation (RAG) has become a cornerstone of knowledge-intensive applications.<n>Recent studies show that knowledge-extraction attacks can recover sensitive knowledge-base content through maliciously crafted queries.<n>We introduce the first systematic benchmark for knowledge-extraction attacks on RAG systems.
  arXiv  Detail & Related papers  (2026-02-10T01:27:46Z)
• Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models [47.866853046761044]
  We find that diverse, subtle patterns in training data can degrade contextual privacy.<n>Fine-tuned models lose their ability to reason about contextual privacy norms.<n>Our results reveal a critical gap in current safety evaluations.
  arXiv  Detail & Related papers  (2026-01-21T17:53:06Z)
• On the MIA Vulnerability Gap Between Private GANs and Diffusion Models [51.53790101362898]
  Generative Adversarial Networks (GANs) and diffusion models have emerged as leading approaches for high-quality image synthesis.<n>We present the first unified theoretical and empirical analysis of the privacy risks faced by differentially private generative models.
  arXiv  Detail & Related papers  (2025-09-03T14:18:22Z)
• Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs [45.265397990158846]
  Video-SafetyBench is the first benchmark designed to evaluate the safety of LVLMs under video-text attacks.<n>It comprises 2,264 video-text pairs spanning 48 fine-grained unsafe categories.<n>To generate semantically accurate videos for safety evaluation, we design a controllable pipeline that decomposes video semantics into subject images and motion text.
  arXiv  Detail & Related papers  (2025-05-17T05:06:38Z)
• The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against "Truly Anonymous" Synthetic Datasets [12.730435519914415]
  We examine the privacy metrics used in real-world synthetic data deployments and demonstrate their unreliability in several ways.<n>We introduce ReconSyn, a reconstruction attack that generates multiple synthetic datasets that are considered private by the metrics but actually leak unique information to individual records.<n>We show that ReconSyn recovers 78-100% of the outliers in the train data with only black-box access to a single fitted generative model and the privacy metrics.
  arXiv  Detail & Related papers  (2023-12-08T15:42:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.