On the Robustness of Face Recognition Algorithms Against Attacks and Bias

Singh, Richa; Agarwal, Akshay; Singh, Maneet; Nagpal, Shruti; Vatsa, Mayank

doi:10.1609/aaai.v34i09.7085

Cited by 64 publications

(31 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Wang and Deng (2019) proposed a reinforcement learning-based race balance network (RL-RBN) to mitigate racial bias. Singh et al (2020) provided a review of techniques related to bias in face recognition.…”

Section: Related Workmentioning

confidence: 99%

Subgroup Invariant Perturbation for Unbiased Pre-Trained Model Prediction

et al. 2021

Self Cite

View full text Add to dashboard Cite

Modern deep learning systems have achieved unparalleled success and several applications have significantly benefited due to these technological advancements. However, these systems have also shown vulnerabilities with strong implications on the fairness and trustability of such systems. Among these vulnerabilities, bias has been an Achilles’ heel problem. Many applications such as face recognition and language translation have shown high levels of bias in the systems towards particular demographic sub-groups. Unbalanced representation of these sub-groups in the training data is one of the primary reasons of biased behavior. To address this important challenge, we propose a two-fold contribution: a bias estimation metric termed as Precise Subgroup Equivalence to jointly measure the bias in model prediction and the overall model performance. Secondly, we propose a novel bias mitigation algorithm which is inspired from adversarial perturbation and uses the PSE metric. The mitigation algorithm learns a single uniform perturbation termed as Subgroup Invariant Perturbation which is added to the input dataset to generate a transformed dataset. The transformed dataset, when given as input to the pre-trained model reduces the bias in model prediction. Multiple experiments performed on four publicly available face datasets showcase the effectiveness of the proposed algorithm for race and gender prediction.

show abstract

Section: Related Workmentioning

confidence: 99%

Subgroup Invariant Perturbation for Unbiased Pre-Trained Model Prediction

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Overall, existing works have demonstrated, beyond doubt, that “morphing” is a threat for face recognition systems. Several survey papers have also highlighted the vulnerability of face recognition algorithm against digital manipulation and limitations of existing detection algorithms ( Akhtar et al, 2019 ; Scherhag et al, 2019 ; Singh et al, 2020 ; Tolosana et al, 2020 ; Venkatesh et al, 2020 ). The survey papers bring out the boundaries of existing detection algorithms such as non-generalizability against manipulation types and image resolution and computationally inefficiency.…”

Section: Related Workmentioning

confidence: 99%

MagNet: Detecting Digital Presentation Attacks on Face Recognition

Singh

Vatsa

Noore

2021

Front. Artif. Intell.

Self Cite

View full text Add to dashboard Cite

Presentation attacks on face recognition systems are classified into two categories: physical and digital. While much research has focused on physical attacks such as photo, replay, and mask attacks, digital attacks such as morphing have received limited attention. With the advancements in deep learning and computer vision algorithms, several easy-to-use applications are available where with few taps/clicks, an image can be easily and seamlessly altered. Moreover, generation of synthetic images or modifying images/videos (e.g. creating deepfakes) is relatively easy and highly effective due to the tremendous improvement in generative machine learning models. Many of these techniques can be used to attack the face recognition systems. To address this potential security risk, in this research, we present a novel algorithm for digital presentation attack detection, termed as MagNet, using a “Weighted Local Magnitude Pattern” (WLMP) feature descriptor. We also present a database, termed as IDAgender, which consists of three different subsets of swapping/morphing and neural face transformation. In contrast to existing research, which utilizes sophisticated machine learning networks for attack generation, the databases in this research are prepared using social media platforms that are readily available to everyone with and without any malicious intent. Experiments on the proposed database, FaceForensic database, GAN generated images, and real-world images/videos show the stimulating performance of the proposed algorithm. Through the extensive experiments, it is observed that the proposed algorithm not only yields lower error rates, but also provides computational efficiency.

show abstract

“…These systems have a growing effect on the daily life [78] and are increasingly involved in critical decisionmaking processes, such as in forensics and law enforcement. However, recent works [49], [4], [24], [53], [7], [25], [63] showed that current face recognition solutions possess biases leading to discriminatory performance differences [59] based on the user's demographics [67], [74].…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Study on Face Recognition Biases Beyond Demographics

Terhörst

Kolf

Huber

et al. 2022

IEEE Trans. Technol. Soc.

View full text Add to dashboard Cite

Face recognition (FR) systems have a growing effect on critical decision-making processes. Recent works have shown that FR solutions show strong performance differences based on the user's demographics. However, to enable a trustworthy FR technology, it is essential to know the influence of an extended range of facial attributes on FR beyond demographics. Therefore, in this work, we analyse FR bias over a wide range of attributes. We investigate the influence of 47 attributes on the verification performance of two popular FR models. The experiments were performed on the publicly available MAAD-Face attribute database with over 120M high-quality attribute annotations. To prevent misleading statements about biased performances, we introduced control group based validity values to decide if unbalanced test data causes the performance differences. The results demonstrate that also many non-demographic attributes strongly affect the recognition performance, such as accessories, hair-styles and colors, face shapes, or facial anomalies. The observations of this work show the strong need for further advances in making FR system more robust, explainable, and fair. Moreover, our findings might help to a better understanding of how FR networks work, to enhance the robustness of these networks, and to develop more generalized bias-mitigating face recognition solutions.

show abstract

On the Robustness of Face Recognition Algorithms Against Attacks and Bias

Cited by 64 publications

References 49 publications

Subgroup Invariant Perturbation for Unbiased Pre-Trained Model Prediction

Subgroup Invariant Perturbation for Unbiased Pre-Trained Model Prediction

MagNet: Detecting Digital Presentation Attacks on Face Recognition

A Comprehensive Study on Face Recognition Biases Beyond Demographics

Contact Info

Product

Resources

About