VideoFlip: Adversarial Bit Flips for Reducing Video Service Quality
Jung-Woo Chang, Mojan Javaheripi, Farinaz Koushanfar
摘要
Video compression is a critical component in streaming applications that maximizes users’ quality of experience (QoE) while satisfying the underlying bandwidth constraints. In this paper, we demonstrate the first hardware-based fault-injection attack on video compression, dubbed VideoFlip. The attack identifies and alters a few bits inside the video compression model to achieve one or more of the following adversarial goals: (1) increasing the bitrate and (2) degrading the quality of the compressed video. Extensive evaluations show VideoFlip irresistibly downgrades video compression performance for various models and video datasets while being resilient to contemporary defenses against hardware-based bit flips.
问问这篇 Paper
问问你的智能体。
Lune 读过与它相关的顶会 Paper,每个回答都会注明依据哪几篇。
引用它的顶会 Paper1
问问它们各自怎么用它相关 Paper
- RoVISQ: Reduction of Video Service Quality via Adversarial Attacks on Deep Learning-based Video CompressionJung-Woo Chang, Mojan Javaheripi, Seira Hidano, Farinaz KoushanfarNDSS 2023
- On the Robustness of Neural-Enhanced Video Streaming against Adversarial AttacksQihua Zhou, Jingcai Guo, Song Guo, Ruibin Li 等AAAI 2024 · 被引用 7 次
- Backdoor Attacks on Neural Networks Via One-Bit FlipXiang Li, Lannan Luo, Qiang ZengICCV 2025 · 被引用 1 次
- Rowhammer-Based Trojan Injection: One Bit Flip Is Sufficient for Backdooring DNNsXiang Li, Ying Meng, Junming Chen, Lannan Luo 等USENIX Security 2025
- DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit FlipsFan Yao, Adnan Siraj Rakin, Deliang FanUSENIX Security 2020
