Privacy Visor: Method Based on Light Absorbing and Reflecting Properties for Preventing Face Image Detection

Yamada, Takayuki; Gohshi, Seiichi; Echizen, Isao

doi:10.1109/smc.2013.271

Cited by 18 publications

(23 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another line of work attempts to achieve privacy from face-recognition systems by completely avoiding face detection [31,79]. Essentially, face detection finds sub-windows in images that contain faces, which are later sent for processing by face-recognition systems.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A General Framework for Adversarial Examples with Objectives

Sharif

Bhagavatula

Bauer

et al. 2019

ACM Trans. Priv. Secur.

159

105

View full text Add to dashboard Cite

Images perturbed subtly to be misclassified by neural networks, called adversarial examples, have emerged as a technically deep challenge and an important concern for several application domains. Most research on adversarial examples takes as its only constraint that the perturbed images are similar to the originals. However, real-world application of these ideas often requires the examples to satisfy additional objectives, which are typically enforced through custom modifications of the perturbation process. In this paper, we propose adversarial generative nets (AGNs), a general methodology to train a generator neural network to emit adversarial examples satisfying desired objectives. We demonstrate the ability of AGNs to accommodate a wide range of objectives, including imprecise ones difficult to model, in two application domains. In particular, we demonstrate physical adversarial examples-eyeglass frames designed to fool face recognition-with better robustness, inconspicuousness, and scalability than previous approaches, as well as a new attack to fool a handwritten-digit classifier. contexts in which it is necessary to model additional objectives of adversarial inputs. For example, our prior work considered a scenario in which adversaries could not manipulate input images directly, but, rather, could only manipulate the physical artifacts captured in such images [68]. Using eyeglasses for fooling face-recognition systems as a driving example, we showed how to encode various objectives into the process of generating eyeglass frames, such as ensuring that the frames were capable of being physically realized by an off-the-shelf printer. As another example, Evtimov et al. considered generating shapes that, when attached to street signs, would seem harmless to human observers, but would lead neural networks to misclassify the signs [20].These efforts modeled the various objectives they considered in an ad hoc fashion. In contrast, in this paper, we propose a general framework for capturing such objectives in the process of generating adversarial inputs. Our framework builds on recent work in generative adversarial networks (GANs) [25] to train an attack generator, i.e., a neural network that can generate successful attack instances that meet certain objectives. Moreover, our framework is not only general, but, unlike previous attacks, produces a large number of diverse adversarial examples that meet the desired objectives. This could be leveraged by an attacker to generate attacks that are unlike previous ones (and hence more likely to succeed), but also by defenders to generate labeled negative inputs to augment training of their classifiers. Due to our framework's basis in GANs, we refer to it using the anagram AGNs, for adversarial generative nets.To illustrate the utility of AGNs, we return to the task of printing eyeglasses to fool facerecognition systems [68] and demonstrate how to accommodate a number of types of objectives within it. Specifically, we use AGNs to accommodate robustness objectives to ensure...

show abstract

Section: Related Workmentioning

confidence: 99%

“…Consequently, by evading detection, one avoids the post processing of her face image by recognition systems. The proposed techniques are not inconspicuous: they either use excessive makeup [31] or attempt to blind the camera using light-emitting eyeglasses [79].…”

Section: Related Workmentioning

confidence: 99%

A General Framework for Adversarial Examples with Objectives

Sharif

Bhagavatula

Bauer

et al. 2019

ACM Trans. Priv. Secur.

159

105

View full text Add to dashboard Cite

show abstract

“…To increase the privacy of first-person cameras for bystanders, researchers have suggested communicating their privacy preferences to nearby capture devices using wireless connections as well as mobile or wearable interfaces [Krombholz et al 2015]. Others have suggested preventing unauthorised recordings by compromising the recorded imagery, e.g., using infra-red light signals [Harvey 2010;Yamada et al 2013] or disturbing face recognition [Harvey 2012]. In contrast to our approach, these techniques all require the bystander to take action, which might be impractical due to costs and efforts .…”

Section: Enhancing Privacy Of First-person Camerasmentioning

confidence: 99%

“…Unlike current computer vision based approaches that work in image space, e.g. by masking objects or faces [Raval et al 2014;Shu et al 2016;Yamada et al 2013], restricting access , or deleting recorded images post-hoc , we de-activate the camera completely using a mechanical shutter and also signal this to bystanders. Our approach is the first to employ eye movement analysis for camera re-activation that, unlike other sensing techniques (e.g., microphones, infra-red cameras), does not compromise the privacy of potential bystanders.…”

Section: Enhancing Privacy Of First-person Camerasmentioning

confidence: 99%

PrivacEye

Steil

Koelle

Heuten

et al. 2019

Proceedings of the 11th ACM Symposium on Eye Tracking Research &Amp; Applications

View full text Add to dashboard Cite

Eyewear devices, such as augmented reality displays, increasingly integrate eye tracking, but the first-person camera required to map a user's gaze to the visual scene can pose a significant threat to user and bystander privacy. We present PrivacEye, a method to detect privacy-sensitive everyday situations and automatically enable and disable the eye tracker's first-person camera using a mechanical shutter. To close the shutter in privacy-sensitive situations, the method uses a deep representation of the first-person video combined with rich features that encode users' eye movements. To open the shutter without visual input, PrivacEye detects changes in users' eye movements alone to gauge changes in the "privacy level" of the current situation. We evaluate our method on a first-person video dataset recorded in daily life situations of 17 participants, annotated by themselves for privacy sensitivity, and show that our method is effective in preserving privacy in this challenging setting. CCS CONCEPTS• Human-centered computing → Interactive systems and tools; Ubiquitous and mobile computing; Ubiquitous and mobile devices; Human computer interaction (HCI).

show abstract

“…His approach was based on manually observing how the detector operates, and did not yield inconspicuous results. With similar goals, Yamada et al leveraged the fact that camera sensors are sensitive to near infra-red light to design light-emitting glasses that can help evade face detection by adding significant noise to the captured image [44]. While effective for evading detection, this technique is neither inconspicuous nor deniable.…”

Section: Related Workmentioning

confidence: 99%

Accessorize to a Crime

Sharif

Bhagavatula

Bauer

et al. 2016

Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security

1,142

145

View full text Add to dashboard Cite

Machine learning is enabling a myriad innovations, including new algorithms for cancer diagnosis and self-driving cars. The broad use of machine learning makes it important to understand the extent to which machine-learning algorithms are subject to attack, particularly when used in applications where physical security or safety is at risk.In this paper, we focus on facial biometric systems, which are widely used in surveillance and access control. We define and investigate a novel class of attacks: attacks that are physically realizable and inconspicuous, and allow an attacker to evade recognition or impersonate another individual. We develop a systematic method to automatically generate such attacks, which are realized through printing a pair of eyeglass frames. When worn by the attacker whose image is supplied to a state-of-the-art face-recognition algorithm, the eyeglasses allow her to evade being recognized or to impersonate another individual. Our investigation focuses on white-box face-recognition systems, but we also demonstrate how similar techniques can be used in black-box scenarios, as well as to avoid face detection.

show abstract

Privacy Visor: Method Based on Light Absorbing and Reflecting Properties for Preventing Face Image Detection

Cited by 18 publications

References 6 publications

A General Framework for Adversarial Examples with Objectives

A General Framework for Adversarial Examples with Objectives

PrivacEye

Accessorize to a Crime

Contact Info

Product

Resources

About