arXiv AI
Jun 9
Vision Language Model Helps Private Information De-Identification in Vision Data
arXiv:2606. 09132v1 Announce Type: new Abstract: Visual Language Models (VLMs) have gained significant popularity due to their remarkable ability.
On the Robustness of Vision-Language Models in Zero-shot Privacy Classification
The paper investigates whether large, instruction‑following Vision‑Language Models (VLMs) can reliably perform zero‑shot image privacy classification. It compares three open‑source VLMs to specialized privacy models on two public benchmarks, evaluating accuracy, robustness to image degradations (compression, lighting changes, noise), inference speed, and parameter count. The findings show that while VLMs remain robust to perturbations, they are less accurate and significantly slower than smaller, purpose‑built privacy models, indicating that scaling alone does not guarantee effective privacy classification.
Related stories
Hugging Face Trending Papers
Jun 8
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges
Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information. However, Multi-modal Large Language Models (MLLMs), which process both text and images, introduce unique privacy challenges that remain underexplored.
arXiv AI
Jun 9
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges
arXiv:2606. 09125v1 Announce Type: cross Abstract: Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information.
arXiv AI
Sep 1
Defending Wearable VLMs Against Private Attribute Inference
arXiv:2608.28691v1 Announce Type: cross Abstract: Wearable VLM pipelines promise continuous multimodal assistance from egocentric visual capture: a user asks a task-driven question about the surround...
arXiv AI
Oct 15
Answer It or Not? Towards Prompt-Adapted Adversarial Images on Vision Language Models
arXiv:2610.16622v1 Announce Type: cross Abstract: With the advancement in language modeling, research on adversarial images has recently shifted from image classifiers to vision-language models (VLMs...
arXiv AI
Aug 28
Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations
The paper argues that evaluating privacy‑enhancing technologies (PETs) solely through image classification is insufficient because classification remains robust to many geometric and local perturbations. It proposes a compute‑aware multi‑task protocol that uses lightweight proxy tasks to assess PETs across various transformations, revealing that PETs with similar classification accuracy can perform very differently on other vision tasks. The study demonstrates the necessity of broader evaluation metrics beyond classification to truly gauge PET effectiveness.
arXiv AI
4d ago
Guided Zero-Shot Anomaly Explanation for Anonymized Crowd Video Monitoring: Context, Categorization, and Spatial Localization
The paper introduces XAVAD, a unified approach for explainable anomaly detection in anonymized crowd video monitoring. It combines zero‑shot anonymization, anomaly type categorization, spatial localization, and scene context description using multimodal CLIP embeddings, LLM‑assisted prompting, and a prompt‑guided patching autofocus mechanism. Experiments on public CCTV datasets show XAVAD outperforms state‑of‑the‑art methods and offers insights into privacy‑explainability trade‑offs.
arXiv AI
Jul 7
PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement
arXiv:2607. 02897v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have shown strong capabilities, but they may memorize private information from web data, raising privacy concerns.
arXiv Computer Vision
2d ago
PrinGS: Privacy Preservation in Gaussian Splatting
PrinGS introduces a privacy‑preserving framework for 3D Gaussian Splatting, enabling post‑training anonymization of sensitive content such as faces, license plates, documents, and computer screens. By localizing and directly anonymizing regions in the 3D representation, the method removes sensitive information from all rendered novel views while maintaining scene geometry and visual fidelity, achieving this in under one second. The approach also offers a privacy‑by‑design training strategy that prevents sensitive data from being encoded during optimization, yielding splats with low face similarity and unreadable text.
arXiv Machine Learning
Jul 9
POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
arXiv:2607. 06649v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sensitive examples could be unintentionally encoded, raising concerns about privacy or copyright violation.
Hugging Face Trending Papers
Jul 7
POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shaking
Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on cross-modal tasks by jointly training on large-scale textual and visual data, where privacy-sensitive examples could be unintentionally encoded, raising concerns about privacy or copyright violation. To this end, Multi-modality Machine Unlearning (MMU) was proposed as a mitigation that can effectively force MLLMs to forget private information.
arXiv Machine Learning
Jul 7
Scalable Differentially Private Data Compression via Diffusion and Stochastic Codes
arXiv:2607. 03392v1 Announce Type: cross Abstract: The ever-increasing collection of personal data has created mounting pressure to develop technologies that protect sensitive aspects of individual identity.