Visor: Privacy-Preserving Video Analytics as a Cloud Service

• URL: http://arxiv.org/abs/2006.09628v2
• Date: Tue, 23 Jun 2020 04:37:24 GMT
• Title: Visor: Privacy-Preserving Video Analytics as a Cloud Service
• Authors: Rishabh Poddar and Ganesh Ananthanarayanan and Srinath Setty and Stavros Volos and Raluca Ada Popa
• Abstract summary: We present Visor, a system that provides confidentiality for the user's video stream as well as the ML models. Visor executes video pipelines in a hybrid TEE that spans both the CPU and GPU. It protects the pipeline against side-channel attacks induced by data-dependent access patterns of video modules.
• Score: 22.967107819620548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video-analytics-as-a-service is becoming an important offering for cloud providers. A key concern in such services is privacy of the videos being analyzed. While trusted execution environments (TEEs) are promising options for preventing the direct leakage of private video content, they remain vulnerable to side-channel attacks. We present Visor, a system that provides confidentiality for the user's video stream as well as the ML models in the presence of a compromised cloud platform and untrusted co-tenants. Visor executes video pipelines in a hybrid TEE that spans both the CPU and GPU. It protects the pipeline against side-channel attacks induced by data-dependent access patterns of video modules, and also addresses leakage in the CPU-GPU communication channel. Visor is up to $1000\times$ faster than na\"ive oblivious solutions, and its overheads relative to a non-oblivious baseline are limited to $2\times$--$6\times$.

Related papers

• NVBleed: Covert and Side-Channel Attacks on NVIDIA Multi-GPU Interconnect [4.573191891034322]
  We explore whether the interconnect on such systems can offer a novel source of leakage, enabling new forms of covert and side-channel attacks. We develop two end-to-end crossGPU side-channel attacks, including application fingerprinting and 3D graphics character identification within Blender. We also discover that leakage surprisingly occurs across Virtual Machines on the Google Cloud Platform.
  arXiv  Detail & Related papers  (2025-03-22T19:52:02Z)
• PipeLLM: Fast and Confidential Large Language Model Services with Speculative Pipelined Encryption [5.667756833450548]
  encryption incurs a significant performance overhead. We introduce PipeLLM, a user-transparent runtime system. We propose speculative pipelined encryption to predict the data requiring encryption.
  arXiv  Detail & Related papers  (2024-11-04T19:58:53Z)
• PPVF: An Efficient Privacy-Preserving Online Video Fetching Framework with Correlated Differential Privacy [24.407782529925615]
  We introduce a novel Privacy-Preserving Video Fetching framework to preserve user request privacy while maintaining high-quality online video services. We use trusted edge devices to pre-fetch and cache videos, ensuring the privacy of users' requests while optimizing the efficiency of edge caching. The results demonstrate that PPVF effectively safeguards user request privacy while upholding high video caching performance.
  arXiv  Detail & Related papers  (2024-08-27T02:03:36Z)
• Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams [78.72965584414368]
  We present Flash-VStream, a video-language model that simulates the memory mechanism of human. Compared to existing models, Flash-VStream achieves significant reductions in latency inference and VRAM consumption. We propose VStream-QA, a novel question answering benchmark specifically designed for online video streaming understanding.
  arXiv  Detail & Related papers  (2024-06-12T11:07:55Z)
• Spatio-temporal Prompting Network for Robust Video Feature Extraction [74.54597668310707]
  Frametemporal is one of the main challenges in the field of video understanding. Recent approaches exploit transformer-based integration modules to obtain quality-of-temporal information. We present a neat and unified framework called N-Temporal Prompting Network (NNSTP) It can efficiently extract video features by adjusting the input features in the network backbone.
  arXiv  Detail & Related papers  (2024-02-04T17:52:04Z)
• Understanding Deep Gradient Leakage via Inversion Influence Functions [53.1839233598743]
  Deep Gradient Leakage (DGL) is a highly effective attack that recovers private training images from gradient vectors. We propose a novel Inversion Influence Function (I$2$F) that establishes a closed-form connection between the recovered images and the private gradients. We empirically demonstrate that I$2$F effectively approximated the DGL generally on different model architectures, datasets, attack implementations, and perturbation-based defenses.
  arXiv  Detail & Related papers  (2023-09-22T17:26:24Z)
• Privacy Side Channels in Machine Learning Systems [87.53240071195168]
  We introduce privacy side channels: attacks that exploit system-level components to extract private information. For example, we show that deduplicating training data before applying differentially-private training creates a side-channel that completely invalidates any provable privacy guarantees. We further show that systems which block language models from regenerating training data can be exploited to exfiltrate private keys contained in the training set.
  arXiv  Detail & Related papers  (2023-09-11T16:49:05Z)
• Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics [3.2872586139884623]
  LtC is a collaborative framework between the video source and the analytics server that efficiently learns to reduce the video streams within an analytics pipeline. LtC is able to use 28-35% less bandwidth and has up to 45% shorter response delay compared to recently published state of the art streaming frameworks.
  arXiv  Detail & Related papers  (2023-07-22T21:36:03Z)
• Large-capacity and Flexible Video Steganography via Invertible Neural Network [60.34588692333379]
  We propose a Large-capacity and Flexible Video Steganography Network (LF-VSN) For large-capacity, we present a reversible pipeline to perform multiple videos hiding and recovering through a single invertible neural network (INN) For flexibility, we propose a key-controllable scheme, enabling different receivers to recover particular secret videos from the same cover video through specific keys.
  arXiv  Detail & Related papers  (2023-04-24T17:51:35Z)
• Real-time Streaming Video Denoising with Bidirectional Buffers [48.57108807146537]
  Real-time denoising algorithms are typically adopted on the user device to remove the noise involved during the shooting and transmission of video streams. Recent multi-output inference works propagate the bidirectional temporal feature with a parallel or recurrent framework. We propose a Bidirectional Streaming Video Denoising framework, to achieve high-fidelity real-time denoising for streaming videos with both past and future temporal receptive fields.
  arXiv  Detail & Related papers  (2022-07-14T14:01:03Z)
• A Serverless Cloud-Fog Platform for DNN-Based Video Analytics with Incremental Learning [31.712746462418693]
  This paper presents the first serverless system that takes full advantage of the client-fog-cloud synergy to better serve the DNN-based video analytics. To this end, we implement a holistic cloud-fog system referred to as V (Video-Platform-as-a-Service) The evaluation demonstrates that V is superior to several SOTA systems: it maintains high accuracy while reducing bandwidth usage by up to 21%, RTT by up to 62.5%, and cloud monetary cost by up to 50%.
  arXiv  Detail & Related papers  (2021-02-05T05:59:36Z)
• Reconfigurable Cyber-Physical System for Critical Infrastructure Protection in Smart Cities via Smart Video-Surveillance [2.2509387878255818]
  We present a reconfigurable Cyber Physical System for the protection of CIs using distributed cloud-edge smart video surveillance. Our local edge nodes perform people detection via Deep Learning. Cloud server gathers results from nodes to carry out biometric facial identification, tracking, and perimeter monitoring.
  arXiv  Detail & Related papers  (2020-11-29T18:43:25Z)

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.