Protecting and Preserving Protest Dynamics for Responsible Analysis

• URL: http://arxiv.org/abs/2604.05256v1
• Date: Mon, 06 Apr 2026 23:46:29 GMT
• Title: Protecting and Preserving Protest Dynamics for Responsible Analysis
• Abstract summary: Protest-related social media data are valuable for understanding collective action but inherently high-risk due to concerns surrounding surveillance, repression, and individual privacy.<n>We propose a responsible computing framework for analyzing collective protest dynamics while reducing risks to individual privacy.
• Score: 2.194367574904039
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Protest-related social media data are valuable for understanding collective action but inherently high-risk due to concerns surrounding surveillance, repression, and individual privacy. Contemporary AI systems can identify individuals, infer sensitive attributes, and cross-reference visual information across platforms, enabling surveillance that poses risks to protesters and bystanders. In such contexts, large foundation models trained on protest imagery risk memorizing and disclosing sensitive information, leading to cross-platform identity leakage and retroactive participant identification. Existing approaches to automated protest analysis do not provide a holistic pipeline that integrates privacy risk assessment, downstream analysis, and fairness considerations. To address this gap, we propose a responsible computing framework for analyzing collective protest dynamics while reducing risks to individual privacy. Our framework replaces sensitive protest imagery with well-labeled synthetic reproductions using conditional image synthesis, enabling analysis of collective patterns without direct exposure of identifiable individuals. We demonstrate that our approach produces realistic and diverse synthetic imagery while balancing downstream analytical utility with reductions in privacy risk. We further assess demographic fairness in the generated data, examining whether synthetic representations disproportionately affect specific subgroups. Rather than offering absolute privacy guarantees, our method adopts a pragmatic, harm-mitigating approach that enables socially sensitive analysis while acknowledging residual risks.

Related papers

• IP Protection in the Era of Visual Generative AI: A Survey [70.06761647752164]
  This survey presents a two-dimensional taxonomy for IP protection in visual generative models.<n>The primary axis is a Control Logic View, which classifies methods into Information Exposure Control, Generative Behavior Constraint, and Attribution & Accountability.<n>The secondary axis distinguishes Data IP from Model IP as cross-cutting asset dimensions.
  arXiv  Detail & Related papers  (2026-08-13T00:26:41Z)
• 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)
• SafeGuard: A Multi-Agent Perception-Reasoning Framework for Social-Risk AI-Generated Video Detection [30.634696315154383]
  We propose SafeGuard, a multi-agent framework that enables collaborative specialization between perception and semantic reasoning.<n>A novel AI-generated video detection benchmark, SafeVid, is introduced to evaluate physical plausibility, structural consistency, and the rationality of social behaviors.
  arXiv  Detail & Related papers  (2026-07-03T08:03:35Z)
• Privacy-Aware Camera 2.0 Technical Report [48.075034699787004]
  Existing privacy-preserving approaches, including physical desensitization, encryption, and obfuscation, often compromise semantic understanding.<n>This paper proposes a novel privacy-preserving perception framework based on the AI Flow paradigm and a collaborative edge-cloud architecture.
  arXiv  Detail & Related papers  (2026-03-05T03:46:20Z)
• SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy [53.75084833636302]
  We propose SIDeR, a Semantic decoupling-driven framework for unrestricted face privacy protection.<n> SIDeR decomposes a facial image into a machine-recognizable identity feature vector and a visually perceptible semantic appearance component.<n>For authorized access, SIDeR can be restored to its original form when the correct password is provided.
  arXiv  Detail & Related papers  (2026-02-04T19:30:48Z)
• A Real-Time Privacy-Preserving Behavior Recognition System via Edge-Cloud Collaboration [45.24567063896216]
  Traditional RGB surveillance raises significant concerns regarding visual recording and storage.<n>Existing privacy-preserving methods compromise semantic understanding capabilities or fail to guarantee mathematical irreversibility against reconstruction attacks.<n>This study presents a novel privacy-preserving perception technology based on the AI Flow theoretical framework and an edge-cloud collaborative architecture.
  arXiv  Detail & Related papers  (2026-01-30T12:55:36Z)
• Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective [18.404146545866812]
  Training generative machine learning models to produce synthetic data has become a popular approach for enhancing privacy in data sharing.<n>As this typically involves processing sensitive personal information, releasing either the trained model or generated synthetic anonymity can still pose privacy risks.<n>We argue that meaningful assessments must account for the capabilities and properties of underlying generative model and be grounded in state-of-the-art privacy attacks.
  arXiv  Detail & Related papers  (2026-01-30T00:57:41Z)
• Single-Pixel Vision-Language Model for Intrinsic Privacy-Preserving Behavioral Intelligence [55.512671026669516]
  We propose the Single-Pixel Vision-Language Model (SP-VLM), a novel framework that reimagines secure environmental monitoring.<n>It achieves intrinsic privacy-by-design by capturing human dynamics through inherently low-dimensional single-pixel modalities.<n>We show that SP-VLM can nonetheless extract meaningful behavioral semantics, enabling robust anomaly detection, people counting, and activity understanding.
  arXiv  Detail & Related papers  (2026-01-21T09:11:26Z)
• The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration [72.33801123508145]
  Large language models (LLMs) are integral to multi-agent systems.<n>Privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations.<n>In particular, seemingly innocuous responses, when composed across interactions, can cumulatively enable adversaries to recover sensitive information.
  arXiv  Detail & Related papers  (2025-09-16T16:57:25Z)
• 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)
• Intermediate Outputs Are More Sensitive Than You Think [3.20091188522012]
  This paper introduces a novel approach to measuring privacy risks in deep computer vision models based on the Degrees of Freedom (DoF) and sensitivity of intermediate outputs.<n>We propose a framework that leverages DoF to evaluate the amount of information retained in each layer and combines this with the rank of the Jacobian matrix to assess sensitivity to input variations.
  arXiv  Detail & Related papers  (2024-12-01T06:40:28Z)
• Proactive Pseudo-Intervention: Causally Informed Contrastive Learning For Interpretable Vision Models [103.64435911083432]
  We present a novel contrastive learning strategy called it Proactive Pseudo-Intervention (PPI) PPI leverages proactive interventions to guard against image features with no causal relevance. We also devise a novel causally informed salience mapping module to identify key image pixels to intervene, and show it greatly facilitates model interpretability.
  arXiv  Detail & Related papers  (2020-12-06T20:30:26Z)
• Systematic Evaluation of Privacy Risks of Machine Learning Models [41.017707772150835]
  We show that prior work on membership inference attacks may severely underestimate the privacy risks. We first propose to benchmark membership inference privacy risks by improving existing non-neural network based inference attacks. We then introduce a new approach for fine-grained privacy analysis by formulating and deriving a new metric called the privacy risk score.
  arXiv  Detail & Related papers  (2020-03-24T00:53:53Z)

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.