AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos

Xiao, Chaowei; Deng, Ruizhi; Li, Bo; Lee, Tae-Sung; Edwards, Benjamin; Yi, Jinfeng; Song, Dawn; Liu, Mingyan; Molloy, Ian

doi:10.1109/iccv.2019.00407

Cited by 47 publications

(44 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Pony et al [191] introduce flickering across the temporal dimension to fool video recognition systems. Xiao et al [192] proposed a defense against attacks on videos that detects adversarial inputs by analysing temporal consistency property of the videos.…”

Section: G Miscellaneous Attacksmentioning

confidence: 99%

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

2018

View full text Add to dashboard Cite

Deep learning is at the heart of the current rise of artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently lead to a large influx of contributions in this direction. This article presents the first comprehensive survey on adversarial attacks on deep learning in Computer Vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

show abstract

Section: G Miscellaneous Attacksmentioning

confidence: 99%

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

2018

View full text Add to dashboard Cite

show abstract

“…Temporal consistency. Leveraging temporal consistency for attack detection has found success in other applications such as wireless sensor networks [7] and object detection for videos [13]. Our work is the first to propose motion as a physical invariant for 3D objects which it leverages to perform temporal consistency checks on 3D point clouds.…”

Section: Background and Related Workmentioning

confidence: 99%

Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perception

You

Hau

Demetriou

2021

Proceedings of the 1st Workshop on Security and Privacy for Mobile AI

View full text Add to dashboard Cite

LiDAR sensors are used widely in Autonomous Vehicles for better perceiving the environment which enables safer driving decisions. Recent work has demonstrated serious LiDAR spoofing attacks with alarming consequences. In particular, model-level LiDAR spoofing attacks aim to inject fake depth measurements to elicit ghost objects that are erroneously detected by 3D Object Detectors, resulting in hazardous driving decisions. In this work, we explore the use of motion as a physical invariant of genuine objects for detecting such attacks. Based on this, we propose a general methodology, 3D Temporal Consistency Check (3D-TC2), which leverages spatiotemporal information from motion prediction to verify objects detected by 3D Object Detectors. Our preliminary design and implementation of a 3D-TC2 prototype demonstrates very promising performance, providing more than 98% attack detection rate with a recall of 91% for detecting spoofed Vehicle (Car) objects, and is able to achieve real-time detection at 41Hz. CCS CONCEPTS• Security and privacy → Intrusion/anomaly detection and malware mitigation; • Computing methodologies → Computer vision; Scene anomaly detection.

show abstract

“…By doing so, the attacker unintentionally affects the scene depth and the anomaly is detected on that output. In [ 79 ], the authors propose AdvIT, a neural network which detects adversarial frames by measuring the temporal consistency of the video. This is accomplished by (1) predicting the current frame using the optical flow from the previous frames, (2) segmenting the predicted and actual current frame using a neural network, and (3) measuring the consistency (cross entropy with the Hadamard product) between the two segmentation maps.…”

Section: Countermeasures and Best Practicesmentioning

confidence: 99%

The Security of IP-Based Video Surveillance Systems

Kalbo

Mirsky

Shabtai

et al. 2020

Sensors

View full text Add to dashboard Cite

Over the last decade, video surveillance systems have become a part of the Internet of Things (IoT). These IP-based surveillance systems now protect industrial facilities, railways, gas stations, and even one’s own home. Unfortunately, like other IoT systems, there are inherent security risks which can lead to significant violations of a user’s privacy. In this review, we explore the attack surface of modern surveillance systems and enumerate the various ways they can be compromised with real examples. We also identify the threat agents, their attack goals, attack vectors, and the resulting consequences of successful attacks. Finally, we present current countermeasures and best practices and discuss the threat horizon. The purpose of this review is to provide researchers and engineers with a better understanding of a modern surveillance systems’ security, to harden existing systems and develop improved security solutions.

show abstract

AdvIT: Adversarial Frames Identifier Based on Temporal Consistency in Videos

Cited by 47 publications

References 16 publications

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perception

The Security of IP-Based Video Surveillance Systems

Contact Info

Product

Resources

About