An official website of the United States government
Although a substantial amount of studies is dedicated to morphing detection, most of them fail to generalize for morph faces outside of their training paradigm. Moreover, recent morph detection methods are highly vulnerable to adversarial attacks. In this paper, we intend to learn a morph detection model with high generalization to a wide range of morphing attacks and high robustness against different adversarial attacks. To this aim, we develop an ensemble of convolutional neural networks (CNNs) and Transformer models to benefit from their capabilities simultaneously. To improve the robust accuracy of the ensemble model, we employ multi-perturbation adversarial training and generate adversarial examples with high transferability for several single models. Our exhaustive evaluations demonstrate that the proposed robust ensemble model generalizes to several morphing attacks and face datasets. In addition, we validate that our robust ensemble model gains better robustness against several adversarial attacks while outperforming the state-of-the-art studies.
more »
« less
Towards Generalizable Morph Attack Detection with Consistency Regularization
Though recent studies have made significant progress in morph attack detection by virtue of deep neural networks, they often fail to generalize well to unseen morph attacks. With numerous morph attacks emerging frequently, generalizable morph attack detection has gained significant attention. This paper focuses on enhancing the generalization capability of morph attack detection from the perspective of consistency regularization. Consistency regularization operates under the premise that generalizable morph attack detection should output consistent predictions irrespective of the possible variations that may occur in the input space. In this work, to reach this objective, two simple yet effective morph-wise augmentations are proposed to explore a wide space of realistic morph transformations in our consistency regularization. Then, the model is regularized to learn consistently at the logit as well as embedding levels across a wide range of morph-wise augmented images. The proposed consistency regularization aligns the abstraction in the hidden layers of our model across the morph attack images which are generated from diverse domains in the wild. Experimental results corroborate the idea and demonstrate the superior generalization and robustness performance of our proposed method compared to the state-of-the-art studies.
more »
« less
- Award ID(s):
- 1650474
- PAR ID:
- 10496387
- Publisher / Repository:
- IEEE
- Date Published:
- Journal Name:
- IEEE Int. Joint Conference on Biometrics (IJCB'23)
- ISBN:
- 979-8-3503-3726-6
- Page Range / eLocation ID:
- 1 to 10
- Format(s):
- Medium: X
- Location:
- Ljubljana, Slovenia
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In cloud computing, it is desirable if suspicious activities can be detected by automatic anomaly detection systems. Although anomaly detection has been investigated in the past, it remains unsolved in cloud computing. Challenges are: characterizing the normal behavior of a cloud server, distinguishing between benign and malicious anomalies (attacks), and preventing alert fatigue due to false alarms. We propose CloudShield, a practical and generalizable real-time anomaly and attack detection system for cloud computing. Cloudshield uses a general, pretrained deep learning model with different cloud workloads, to predict the normal behavior and provide real-time and continuous detection by examining the model reconstruction error distributions. Once an anomaly is detected, to reduce alert fatigue, CloudShield automatically distinguishes between benign programs, known attacks, and zero-day attacks, by examining the prediction error distributions. We evaluate the proposed CloudShield on representative cloud benchmarks. Our evaluation shows that CloudShield, using model pretraining, can apply to a wide scope of cloud workloads. Especially, we observe that CloudShield can detect the recently proposed speculative execution attacks, e.g., Spectre and Meltdown attacks, in milliseconds. Furthermore, we show that CloudShield accurately differentiates and prioritizes known attacks, and potential zero-day attacks, from benign programs. Thus, it significantly reduces false alarms by up to 99.0%.more » « less
-
Parameter-space regularization in neural network optimization is a fundamental tool for improving generalization. However, standard parameter-space regularization methods make it challenging to encode explicit preferences about desired predictive functions into neural network training. In this work, we approach regularization in neural networks from a probabilistic perspective and show that by viewing parameter-space regularization as specifying an empirical prior distribution over the model parameters, we can derive a probabilistically well-motivated regularization technique that allows explicitly encoding information about desired predictive functions into neural network training. This method—which we refer to as function-space empirical Bayes (FS-EB)—includes both parameter- and function-space regularization, is mathematically simple, easy to implement, and incurs only minimal computational overhead compared to standard regularization techniques. We evaluate the utility of this regularization technique empirically and demonstrate that the proposed method leads to near-perfect semantic shift detection, highly-calibrated predictive uncertainty estimates, successful task adaption from pre-trained models, and improved generalization under covariate shift.more » « less
-
Intrusion detection systems are a commonly deployed defense that examines network traffic, host operations, or both to detect attacks. However, more attacks bypass IDS defenses each year, and with the sophistication of attacks increasing as well, we must examine new perspectives for intrusion detection. Current intrusion detection systems focus on known attacks and/or vulnerabilities, limiting their ability to identify new attacks, and lack the visibility into all system components necessary to confirm attacks accurately, particularly programs. To change the landscape of intrusion detection, we propose that future IDSs track how attacks evolve across system layers by adapting the concept of attack graphs. Attack graphs were proposed to study how multi-stage attacks could be launched by exploiting known vulnerabilities. Instead of constructing attacks reactively, we propose to apply attack graphs proactively to detect sequences of events that fulfill the requirements for vulnerability exploitation. Using this insight, we examine how to generate modular attack graphs automatically that relate adversary accessibility for each component, called its attack surface, to flaws that provide adversaries with permissions that create threats, called attack states, and exploit operations from those threats, called attack actions. We evaluate the proposed approach by applying it to two case studies: (1) attacks on file retrieval, such as TOCTTOU attacks, and (2) attacks propagated among processes, such as attacks on Shellshock vulnerabilities. In these case studies, we demonstrate how to leverage existing tools to compute attack graphs automatically and assess the effectiveness of these tools for building complete attack graphs. While we identify some research areas, we also find several reasons why attack graphs can provide a valuable foundation for improving future intrusion detection systems.more » « less
-
Neural Radiance Fields (NeRF) have become an increasingly popular representation to capture high-quality appearance and shape of scenes and objects. However, learning generalizable NeRF priors over categories of scenes or objects has been challenging due to the high dimensionality of network weight space. To address the limitations of existing work on generalization, multi-view consistency and to improve quality, we propose HyP-NeRF, a latent conditioning method for learning generalizable category-level NeRF priors using hypernetworks. Rather than using hypernetworks to estimate only the weights of a NeRF, we estimate both the weights and the multi-resolution hash encodings resulting in significant quality gains. To improve quality even further, we incorporate a denoise and finetune strategy that denoises images rendered from NeRFs estimated by the hypernetwork and finetunes it while retaining multiview consistency. These improvements enable us to use HyP-NeRF as a generalizable prior for multiple downstream tasks including NeRF reconstruction from single-view or cluttered scenes and text-to-NeRF. We provide qualitative comparisons and evaluate HyP-NeRF on three tasks: generalization, compression, and retrieval, demonstrating our state-of-the-art results.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/IJCB57857.2023.10448876
