SecureFace: Face Template Protection Mai, Guangcan; Cao, Kai; Lan, Xiangyuan ...
IEEE transactions on information forensics and security,
01/2021, Volume:
16
Journal Article
Peer reviewed
It has been shown that face images can be reconstructed from their representations (templates). We propose a randomized CNN to generate protected face biometric templates given the input face image ...and a user-specific key. The use of user-specific keys introduces randomness to the secure template and hence strengthens the template security. To further enhance the security of the templates, instead of storing the key, we store a secure sketch that can be decoded to generate the key with genuine queries submitted to the system. We have evaluated the proposed protected template generation method using three benchmarking datasets for the face (FRGC v2.0, CFP, and IJB-A). The experimental results justify that the protected template generated by the proposed method are non-invertible and cancellable, while preserving the verification performance.
State-of-the-art face recognition systems are based on deep (convolutional) neural networks. Therefore, it is imperative to determine to what extent face templates derived from deep networks can be ...inverted to obtain the original face image. In this paper, we study the vulnerabilities of a state-of-the-art face recognition system based on template reconstruction attack. We propose a neighborly de-convolutional neural network (NbNet) to reconstruct face images from their deep templates. In our experiments, we assumed that no knowledge about the target subject and the deep network are available. To train the NbNet reconstruction models, we augmented two benchmark face datasets (VGG-Face and Multi-PIE) with a large collection of images synthesized using a face generator. The proposed reconstruction was evaluated using type-I (comparing the reconstructed images against the original face images used to generate the deep template) and type-II (comparing the reconstructed images against a different face image of the same subject) attacks. Given the images reconstructed from NbNets, we show that for verification, we achieve TAR of 95.20 percent (58.05 percent) on LFW under type-I (type-II) attacks @ FAR of 0.1 percent. Besides, 96.58 percent (92.84 percent) of the images reconstructed from templates of partition fa (fb) can be identified from partition fa in color FERET. Our study demonstrates the need to secure deep templates in face recognition systems.
Object detection is a fundamental challenge encountered in understanding and analyzing remote sensing images. Many current detection methods struggle to identify objects in remote sensing images due ...to poor feature saliency, diverse directions, and unique viewing angles of small remote sensing targets. As most remote sensing images are captured through overhead photography, the structural contour features of objects in these images remain relatively stable, such as the cross-shaped structure of the aircraft and the rectangular structure of the vehicle. Therefore, we utilize the physical simulation images as prior knowledge to supplement the invariant structural features of the target, extract the target's key geometric features through the dynamic matching method, and fuse it with the features extracted by the neural network to detect the remote sensing small target more effectively in this paper. We propose a template matching method based on physical simulation images (TMSI) and add it to the modified Darknet-53 (named TMSI-Net) for small target detection. Based on this, we perform specific transformations on existing templates in terms of target scale and direction to achieve better adaptation to the corresponding goals and propose DTMSI-Net with a dynamic template library (Dynamic TMSI-Net). Experiments on several datasets demonstrate that the DTMSI-Net exhibits higher detection accuracy and more stable performance compared with the state-of-the-art methods, 4% and 2.7% higher than the second-ranked model on the VEDAI and NWPU datasets, respectively.
Much of the success of fingerprint recognition is attributed to minutiae-based fingerprint representation. It was believed that minutiae templates could not be inverted to obtain a high fidelity ...fingerprint image, but this assumption has been shown to be false. The success of deep learning has resulted in alternative fingerprint representations (embeddings), in the hope that they might offer better recognition accuracy as well as non-invertibility of deep network-based templates. We evaluate whether deep fingerprint templates suffer from the same reconstruction attacks as the minutiae templates. We show that while a deep template can be inverted to produce a fingerprint image that could be matched to its source image, deep templates are more resistant to reconstruction attacks than minutiae templates. In particular, reconstructed fingerprint images from minutiae templates yield a TAR of about 100.0% (98.3%) @ FAR of 0.01% for type-I (type-II) attacks using a state-of-the-art commercial fingerprint matcher, when tested on NIST SD4. The corresponding attack performance for reconstructed fingerprint images from deep templates using the same commercial matcher yields a TAR of less than 1% for both type-I and type-II attacks; however, when the reconstructed images are matched using the same deep network, they achieve a TAR of 85.95% (68.10%) for type-I (type-II) attacks. Furthermore, what is missing from previous fingerprint template inversion studies is an evaluation of the black-box attack performance, which we perform using 3 different state-of-the-art fingerprint matchers. We conclude that fingerprint images generated by inverting minutiae templates are highly susceptible to both white-box and black-box attack evaluations, while fingerprint images generated by deep templates are resistant to black-box evaluations and comparatively less susceptible to white-box evaluations.
Nanocasting is a powerful method for creating materials that are more difficult to synthesize by conventional processes. We summarize recent developments in the synthesis of various structured porous ...solids, covering silica, carbon, and other nonsiliceous solids that are created by a nanocasting pathway. Structure replication on the nanometer length scale allows materials' properties to be manipulated in a controlled manner, such as tunable composition, controllable structure and morphology, and specific functionality. The nanocasting pathway with hard templates opens the door to the design of highly porous solids with multifunctional properties and interesting application perspectives.
The nanocasting pathway from hard templates, a versatile synthetic strategy, has successfully been applied for the creation of porous solids (see figure). The obtained structures can be precisely tailored by selecting a suitable template, precursor, and synthetic conditions, and the resulting materials lend themselves to further, spatially controlled modification.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
While most research on attentional templates focuses on how attention can be guided toward targets, a growing body of research has been examining our ability to guide attention away from distractors ...using negative templates. A recent report showed larger reaction time benefits from negative templates during a difficult search task compared to an easy search task. However, it remains unclear what shifts in attentional processing led to these differences in reaction time benefits. In the current study, we tested the predictions of enhanced guidance and rapid rejection as potential explanations for the differential impact of negative templates based on search difficulty. In Experiment 1, we replicated the larger benefits from negative templates in a within-subjects design. In Experiment 2, we use eye tracking to measure the proportion of fixations directed towards target-colored distractors as an index of enhanced guidance and the dwell time on distractors as a measure of rapid rejection. We found more attentional guidance from negative templates in the difficult search condition. In addition, we found larger benefits of rapid rejection from negative templates in the difficult search condition. While we typically focus on templates as a way of guiding attention, these results highlight another key role played by attentional templates: rapid distractor rejection.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Qualitative research can offer meaningful insights into the complexities of family businesses and inspire and inform theory development in family business as well as other fields. Unlike in ...quantitative approaches, there are no general standards for conducting and reporting qualitative research. In lieu of such standards, following templates in previously published papers has become a popular means of establishing a certain level of standardization in qualitative research. However, recent discussions about the detriments of mindless template use have highlighted the dangers of inappropriate standardization for research quality of qualitative research. This article raises awareness of the challenges and inherent risks of template prescriptions in qualitative family business research and proposes alternative avenues going forward. Scholars, as well as journal editors and reviewers, may take inspiration and orientation from these alternatives to harness the diversity and core strengths of qualitative family business research without enforcing generalized standards.
•We raise awareness of the challenges and inherent risks of template prescriptions in qualitative family business research.•We lean on similar discussions from mainstream management research.•We outline four ways forward and provide concrete suggestions how these approaches might be implemented in future research.•We offer inspiration and orientation to scholars, editors and reviewers for conducting and evaluating qualitative research.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
► A novel ordered mesoporous Co(OH)
2 nanowires structure has been successfully fabricated. ► The mesoporous ordered hexagonal structure with cylindrical channels in Co(OH)
2 nanowires was obtained. ...► A capacitance of 993
F
g
−1 for the mesoporous Co(OH)
2 nanowire array was obtained.
A novel ordered mesoporous Co(OH)
2 nanowire structure has been successfully fabricated by a dual-template method utilizing porous anodic alumina (PAA) and lyotropic liquid crystal (LLC) through potentiostatic electrodeposition technique. The mesoporous ordered hexagonal structure with cylindrical channels in Co(OH)
2 nanowires is confirmed by low-angle X-ray diffraction (XRD) and transmission electron microscopy (TEM). A capacitance of 993
F
g
−1 for the mesoporous Co(OH)
2 nanowire array is obtained from charge/discharge measurement at current density of 1
A
g
−1, indicating that the unique mesoporous nanowire structure can enhance its electrochemical properties.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
In the ligand prediction category of CASP15, the challenge was to predict the positions and conformations of small molecules binding to proteins that were provided as amino acid sequences or as ...models generated by the AlphaFold2 program. For most targets, we used our template‐based ligand docking program ClusPro ligTBM, also implemented as a public server available at https://ligtbm.cluspro.org/. Since many targets had multiple chains and a number of ligands, several templates, and some manual interventions were required. In a few cases, no templates were found, and we had to use direct docking using the Glide program. Nevertheless, ligTBM was shown to be a very useful tool, and by any ranking criteria, our group was ranked among the top five best‐performing teams. In fact, all the best groups used template‐based docking methods. Thus, it appears that the AlphaFold2‐generated models, despite the high accuracy of the predicted backbone, have local differences from the x‐ray structure that make the use of direct docking methods more challenging. The results of CASP15 confirm that this limitation can be frequently overcome by homology‐based docking.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
A systematic study has been carried out on the 3d divalent metal formate 3D magnetic frameworks templated by protonated amines, and the achievements have revealed that metal formate frameworks are ...very malleable, and their structures depend on the size, shape, charge, and hydrogen bonding geometries of the templating cations. Six kinds of metal formate frameworks have been created. They are chiral frameworks with a (49 · 66) topology, perovskite ones with a (412 · 63) topology, bi‐nodal frameworks of (412 · 63)(49 · 66)n (n = 1, 2, 3) topologies, and porous diamond frameworks with 66 topology. These materials display promising and abundant magnetic, dielectric, porous, and optical properties and the possible combination of them. Therefore, they are of great interest for the study of molecule‐based materials. It has been demonstrated that formate, being the smallest and simplest carboxylate, cheap and with low toxicity, thus more biocompatible and environmentally friendly, and having been more or less ignored, will find an important role in the construction of molecule‐based materials and provide new materials with interesting properties.
A study of the 3d divalent metal formates, templated by protonated amines, has created chiral (49 · 66), perovskite (412 · 63), bi‐nodal (412 · 63)(49 · 66)n (n = 1 to 3), and diamond 66 metal formate frameworks, depending on the templates used. These materials display various magnetic, dielectric, porous, and optical properties, and combinations thereof. It is expected that the more or less ignored formate will play an important role in the study of molecule‐based materials.
Full text
Available for:
BFBNIB, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK