The Latest Papers about AI
-
Gender Bias in Text: Labeled Datasets and Lexicons
2022-01-21 12:44:51Jad Doughman, Wael KhreichAbstract
Language has a profound impact on our thoughts, perceptions, and conceptions of gender roles. Gender-inclusive language is, therefore, a key tool to promote social inclusion and contribute to achieving gender equality. Consequently, detecting and mitigating gender bias in texts is instrumental in halting its propagation and societal implications. However, there is a lack of gender bias datasets and lexicons for automating the detection of gender bias using supervised and unsupervised machine learning (ML) and natural language processing (NLP) techniques. Therefore, the main contribution of this work is to publicly provide labeled datasets and exhaustive lexicons by collecting, annotating, and augmenting relevant sentences to facilitate the detection of gender bias in English text. Towards this end, we present an updated version of our previously proposed taxonomy by re-formalizing its structure, adding a new bias type, and mapping each bias subtype to an appropriate detection methodology. The released datasets and lexicons span multiple bias subtypes including: Generic He, Generic She, Explicit Marking of Sex, and Gendered Neologisms. We leveraged the use of word embedding models to further augment the collected lexicons. The underlying motivation of our work is to enable the technical community to combat gender bias in text and halt its propagation using ML and NLP techniques.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08675
PDF
-
Exploring Fusion Strategies for Accurate RGBT Visual Object Tracking
2022-01-21 12:37:43Zhangyong Tang (1), Tianyang Xu (1), Hui Li (1), Xiao-Jun Wu (1), Xuefeng Zhu (1), Josef Kittler (2) ((1) Jiangnan University, Wuxi, China, (2) University of Surrey, UK)Abstract
We address the problem of multi-modal object tracking in video and explore various options of fusing the complementary information conveyed by the visible (RGB) and thermal infrared (TIR) modalities including pixel-level, feature-level and decision-level fusion. Specifically, different from the existing methods, paradigm of image fusion task is heeded for fusion at pixel level. Feature-level fusion is fulfilled by attention mechanism with channels excited optionally. Besides, at decision level, a novel fusion strategy is put forward since an effortless averaging configuration has shown the superiority. The effectiveness of the proposed decision-level fusion strategy owes to a number of innovative contributions, including a dynamic weighting of the RGB and TIR contributions and a linear template update operation. A variant of which produced the winning tracker at the Visual Object Tracking Challenge 2020 (VOT-RGBT2020). The concurrent exploration of innovative pixel- and feature-level fusion strategies highlights the advantages of the proposed decision-level fusion method. Extensive experimental results on three challenging datasets, \textit{i.e.}, GTOT, VOT-RGBT2019, and VOT-RGBT2020, demonstrate the effectiveness and robustness of the proposed method, compared to the state-of-the-art approaches. Code will be shared at \textcolor{blue}{\emph{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08673
PDF
-
Random Noise vs State-of-the-Art Probabilistic Forecasting Methods : A Case Study on CRPS-Sum Discrimination Ability
2022-01-21 12:36:58Alireza Koochali, Peter Schichtel, Andreas Dengel, Sheraz AhmedAbstract
The recent developments in the machine learning domain have enabled the development of complex multivariate probabilistic forecasting models. Therefore, it is pivotal to have a precise evaluation method to gauge the performance and predictability power of these complex methods. To do so, several evaluation metrics have been proposed in the past (such as Energy Score, Dawid-Sebastiani score, variogram score), however, they cannot reliably measure the performance of a probabilistic forecaster. Recently, CRPS-sum has gained a lot of prominence as a reliable metric for multivariate probabilistic forecasting. This paper presents a systematic evaluation of CRPS-sum to understand its discrimination ability. We show that the statistical properties of target data affect the discrimination ability of CRPS-Sum. Furthermore, we highlight that CRPS-Sum calculation overlooks the performance of the model on each dimension. These flaws can lead us to an incorrect assessment of model performance. Finally, with experiments on the real-world dataset, we demonstrate that the shortcomings of CRPS-Sum provide a misleading indication of the probabilistic forecasting performance method. We show that it is easily possible to have a better CRPS-Sum for a dummy model, which looks like random noise, in comparison to the state-of-the-art method.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08671
PDF
-
Context-Tuning: Learning Contextualized Prompts for Natural Language Generation
2022-01-21 12:35:28Tianyi Tang, Junyi Li, Wayne Xin ZhaoAbstract
Recently, pretrained language models (PLMs) have made exceptional success in language generation. To leverage the rich knowledge encoded by PLMs, a simple yet powerful mechanism is to use prompts, in the form of either discrete tokens or continuous embeddings. In existing studies, manual prompts are time-consuming and require domain expertise, while continuous prompts are typically independent of the inputs. To address this issue, we propose a novel continuous prompting approach, called Context-Tuning, to fine-tuning PLMs for natural language generation. Firstly, the prompts are derived based on the input text, so that they can elicit useful knowledge from PLMs for generation. We refer to such prompts as contextualized prompts. Secondly, to further enhance the relevance of the generated text to the inputs, we utilize continuous inverse prompting to refine the process of natural language generation by modeling an inverse generation process from output to input. Moreover, we propose a lightweight contexttuning, fine-tuning only 0.4% of parameters while retaining well performance.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08670
PDF
-
Dynamic Deep Convolutional Candlestick Learner
2022-01-21 12:34:59Jun-Hao Chen, Yun-Cheng TsaiAbstract
Candlestick pattern is one of the most fundamental and valuable graphical tools in financial trading that supports traders observing the current market conditions to make the proper decision. This task has a long history and, most of the time, human experts. Recently, efforts have been made to automatically classify these patterns with the deep learning models. The GAF-CNN model is a well-suited way to imitate how human traders capture the candlestick pattern by integrating spatial features visually. However, with the great potential of the GAF encoding, this classification task can be extended to a more complicated object detection level. This work presents an innovative integration of modern object detection techniques and GAF time-series encoding on candlestick pattern tasks. We make crucial modifications to the representative yet straightforward YOLO version 1 model based on our time-series encoding method and the property of such data type. Powered by the deep neural networks and the unique architectural design, the proposed model performs pretty well in candlestick classification and location recognition. The results show tremendous potential in applying modern object detection techniques on time-series tasks in a real-time manner.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08669
PDF
-
Fast Differentiable Matrix Square Root
Abstract
Computing the matrix square root or its inverse in a differentiable manner is important in a variety of computer vision tasks. Previous methods either adopt the Singular Value Decomposition (SVD) to explicitly factorize the matrix or use the Newton-Schulz iteration (NS iteration) to derive the approximate solution. However, both methods are not computationally efficient enough in either the forward pass or in the backward pass. In this paper, we propose two more efficient variants to compute the differentiable matrix square root. For the forward propagation, one method is to use Matrix Taylor Polynomial (MTP), and the other method is to use Matrix Padé Approximants (MPA). The backward gradient is computed by iteratively solving the continuous-time Lyapunov equation using the matrix sign function. Both methods yield considerable speed-up compared with the SVD or the Newton-Schulz iteration. Experimental results on the de-correlated batch normalization and second-order vision transformer demonstrate that our methods can also achieve competitive and even slightly better performances. The code is available at \href{this https URL}{this https URL}.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08663
PDF
-
On the adaptation of recurrent neural networks for system identification
2022-01-21 12:04:17Marco Forgione, Aneri Muni, Dario Piga, Marco GallieriAbstract
This paper presents a transfer learning approach which enables fast and efficient adaptation of Recurrent Neural Network (RNN) models of dynamical systems. A nominal RNN model is first identified using available measurements. The system dynamics are then assumed to change, leading to an unacceptable degradation of the nominal model performance on the perturbed system. To cope with the mismatch, the model is augmented with an additive correction term trained on fresh data from the new dynamic regime. The correction term is learned through a Jacobian Feature Regression (JFR) method defined in terms of the features spanned by the model's Jacobian with respect to its nominal parameters. A non-parametric view of the approach is also proposed, which extends recent work on Gaussian Process (GP) with Neural Tangent Kernel (NTK-GP) to the RNN case (RNTK-GP). This can be more efficient for very large networks or when only few data points are available. Implementation aspects for fast and efficient computation of the correction term, as well as the initial state estimation for the RNN model are described. Numerical examples show the effectiveness of the proposed methodology in presence of significant system variations.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08660
PDF
-
Enhancing Pseudo Label Quality for Semi-SupervisedDomain-Generalized Medical Image Segmentation
Abstract
Generalizing the medical image segmentation algorithms tounseen domains is an important research topic for computer-aided diagnosis and surgery. Most existing methods requirea fully labeled dataset in each source domain. Although (Liuet al. 2021b) developed a semi-supervised domain general-ized method, it still requires the domain labels. This paperpresents a novel confidence-aware cross pseudo supervisionalgorithm for semi-supervised domain generalized medicalimage segmentation. The main goal is to enhance the pseudolabel quality for unlabeled images from unknown distribu-tions. To achieve it, we perform the Fourier transformationto learn low-level statistic information across domains andaugment the images to incorporate cross-domain information.With these augmentations as perturbations, we feed the inputto a confidence-aware cross pseudo supervision network tomeasure the variance of pseudo labels and regularize the net-work to learn with more confident pseudo labels. Our methodsets new records on public datasets,i.e., M&Ms and SCGM.Notably, without using domain labels, our method surpassesthe prior art that even uses domain labels by 11.67% on Diceon M&Ms dataset with 2% labeled data. Code will be avail-able after the conference.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08657
PDF
-
Text Style Transfer for Bias Mitigation using Masked Language Modeling
2022-01-21 11:06:33Ewoenam Kwaku Tokpo, Toon CaldersAbstract
It is well known that textual data on the internet and other digital platforms contain significant levels of bias and stereotypes. Although many such texts contain stereotypes and biases that inherently exist in natural language for reasons that are not necessarily malicious, there are crucial reasons to mitigate these biases. For one, these texts are being used as training corpus to train language models for salient applications like cv-screening, search engines, and chatbots; such applications are turning out to produce discriminatory results. Also, several research findings have concluded that biased texts have significant effects on the target demographic groups. For instance, masculine-worded job advertisements tend to be less appealing to female applicants. In this paper, we present a text style transfer model that can be used to automatically debias textual data. Our style transfer model improves on the limitations of many existing style transfer techniques such as loss of content information. Our model solves such issues by combining latent content encoding with explicit keyword replacement. We will show that this technique produces better content preservation whilst maintaining good style transfer accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08643
PDF
-
Conceptor Learning for Class Activation Mapping
2022-01-21 10:51:14Guangwu Qian, Zhen-Qun Yang, Xu-Lu Zhang, Yaowei Wang, Qing Li, Xiao-Yong WeiAbstract
Class Activation Mapping (CAM) has been widely adopted to generate saliency maps which provides visual explanations for deep neural networks (DNNs). The saliency maps are conventionally generated by fusing the channels of the target feature map using a weighted average scheme. It is a weak model for the inter-channel relation, in the sense that it only models the relation among channels in a contrastive way (i.e., channels that play key roles in the prediction are given higher weights for them to stand out in the fusion). The collaborative relation, which makes the channels work together to provide cross reference, has been ignored. Furthermore, the model has neglected the intra-channel relation this http URL this paper, we address this problem by introducing Conceptor learning into CAM generation. Conceptor leaning has been originally proposed to model the patterns of state changes in recurrent neural networks (RNNs). By relaxing the dependency of Conceptor learning to RNNs, we make Conceptor-CAM not only generalizable to more DNN architectures but also able to learn both the inter- and intra-channel relations for better saliency map generation. Moreover, we have enabled the use of Boolean operations to combine the positive and pseudo-negative evidences, which has made the CAM inference more robust and comprehensive. The effectiveness of Conceptor-CAM has been validated with both formal verifications and experiments on the dataset of the largest scale in literature. The experimental results show that Conceptor-CAM is compatible with and can bring significant improvement to all well recognized CAM-based methods, and has outperformed the state-of-the-art methods by 43.14%~72.79% (88.39%~168.15%) on ILSVRC2012 in Average Increase (Drop), 15.42%~42.55% (47.09%~372.09%) on VOC, and 17.43%~31.32% (47.54%~206.45%) on COCO, respectively.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08636
PDF
-
Multi-view Monocular Depth and Uncertainty Prediction with Deep SfM in Dynamic Environments
2022-01-21 10:42:57Christian Homeyer, Oliver Lange, Christoph SchnörrAbstract
3D reconstruction of depth and motion from monocular video in dynamic environments is a highly ill-posed problem due to scale ambiguities when projecting to the 2D image domain. In this work, we investigate the performance of the current State-of-the-Art (SotA) deep multi-view systems in such environments. We find that current supervised methods work surprisingly well despite not modelling individual object motions, but make systematic errors due to a lack of dense ground truth data. To detect such errors during usage, we extend the cost volume based Deep Video to Depth (DeepV2D) framework \cite{teed2018deepv2d} with a learned uncertainty. Our Deep Video to certain Depth (DeepV2cD) model allows i) to perform en par or better with current SotA and ii) achieve a better uncertainty measure than the naive Shannon entropy. Our experiments show that a simple filter strategy based on the uncertainty can significantly reduce systematic errors. This results in cleaner reconstructions both on static and dynamic parts of the scene.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08633
PDF
-
Efficient Globally Optimal 2D-to-3D Deformable Shape Matching
2022-01-21 10:37:35Zorah Lähner, Emanuele Rodolà, Frank R. Schmidt, Michael M. Bronstein, Daniel CremersAbstract
We propose the first algorithm for non-rigid 2D-to-3D shape matching, where the input is a 2D shape represented as a planar curve and a 3D shape represented as a surface; the output is a continuous curve on the surface. We cast the problem as finding the shortest circular path on the product 3-manifold of the surface and the curve. We prove that the optimal matching can be computed in polynomial time with a (worst-case) complexity of $O(mn^2\log(n))$, where $m$ and $n$ denote the number of vertices on the template curve and the 3D shape respectively. We also demonstrate that in practice the runtime is essentially linear in $m\!\cdot\! n$ making it an efficient method for shape analysis and shape retrieval. Quantitative evaluation confirms that the method provides excellent results for sketch-based deformable 3D shape retrieval.
Abstract (translated)
URL
https://arxiv.org/abs/1601.06070
PDF
-
VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
2022-01-21 10:20:52Attila Lengyel, Robert-Jan Bruintjes, Marcos Baptista Rios, Osman Semih Kayhan, Davide Zambrano, Nergis Tomen, Jan van GemertAbstract
The second edition of the "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges featured five data-impaired challenges, where models are trained from scratch on a reduced number of training samples for various key computer vision tasks. To encourage new and creative ideas on incorporating relevant inductive biases to improve the data efficiency of deep learning models, we prohibited the use of pre-trained checkpoints and other transfer learning techniques. The provided baselines are outperformed by a large margin in all five challenges, mainly thanks to extensive data augmentation policies, model ensembling, and data efficient network architectures.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08625
PDF
-
Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World
2022-01-21 10:11:27Hua Ma, Yinshan Li, Yansong Gao, Alsharif Abuadbba, Zhi Zhang, Anmin Fu, Hyoungshick Kim, Said F. Al-Sarawi, Nepal Surya, Derek AbbottAbstract
Deep learning models have been shown to be vulnerable to recent backdoor attacks. A backdoored model behaves normally for inputs containing no attacker-secretly-chosen trigger and maliciously for inputs with the trigger. To date, backdoor attacks and countermeasures mainly focus on image classification tasks. And most of them are implemented in the digital world with digital triggers. Besides the classification tasks, object detection systems are also considered as one of the basic foundations of computer vision tasks. However, there is no investigation and understanding of the backdoor vulnerability of the object detector, even in the digital world with digital triggers. For the first time, this work demonstrates that existing object detectors are inherently susceptible to physical backdoor attacks. We use a natural T-shirt bought from a market as a trigger to enable the cloaking effect--the person bounding-box disappears in front of the object detector. We show that such a backdoor can be implanted from two exploitable attack scenarios into the object detector, which is outsourced or fine-tuned through a pretrained model. We have extensively evaluated three popular object detection algorithms: anchor-based Yolo-V3, Yolo-V4, and anchor-free CenterNet. Building upon 19 videos shot in real-world scenes, we confirm that the backdoor attack is robust against various factors: movement, distance, angle, non-rigid deformation, and lighting. Specifically, the attack success rate (ASR) in most videos is 100% or close to it, while the clean data accuracy of the backdoored model is the same as its clean counterpart. The latter implies that it is infeasible to detect the backdoor behavior merely through a validation set. The averaged ASR still remains sufficiently high to be 78% in the transfer learning attack scenarios evaluated on CenterNet. See the demo video on this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08619
PDF
-
Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization
2022-01-21 09:51:58Can Wang, Sheng Jin, Yingda Guan, Wentao Liu, Chen Qian, Ping Luo, Wanli OuyangAbstract
Localizing keypoints of an object is a basic visual problem. However, supervised learning of a keypoint localization network often requires a large amount of data, which is expensive and time-consuming to obtain. To remedy this, there is an ever-growing interest in semi-supervised learning (SSL), which leverages a small set of labeled data along with a large set of unlabeled data. Among these SSL approaches, pseudo-labeling (PL) is one of the most popular. PL approaches apply pseudo-labels to unlabeled data, and then train the model with a combination of the labeled and pseudo-labeled data iteratively. The key to the success of PL is the selection of high-quality pseudo-labeled samples. Previous works mostly select training samples by manually setting a single confidence threshold. We propose to automatically select reliable pseudo-labeled samples with a series of dynamic thresholds, which constitutes a learning curriculum. Extensive experiments on six keypoint localization benchmark datasets demonstrate that the proposed approach significantly outperforms the previous state-of-the-art SSL approaches.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08613
PDF
-
Taxonomy Enrichment with Text and Graph Vector Representations
2022-01-21 09:01:12Irina Nikishina, Mikhail Tikhomirov, Varvara Logacheva, Yuriy Nazarov, Alexander Panchenko, Natalia LoukachevitchAbstract
Knowledge graphs such as DBpedia, Freebase or Wikidata always contain a taxonomic backbone that allows the arrangement and structuring of various concepts in accordance with the hypo-hypernym ("class-subclass") relationship. With the rapid growth of lexical resources for specific domains, the problem of automatic extension of the existing knowledge bases with new words is becoming more and more widespread. In this paper, we address the problem of taxonomy enrichment which aims at adding new words to the existing taxonomy. We present a new method that allows achieving high results on this task with little effort. It uses the resources which exist for the majority of languages, making the method universal. We extend our method by incorporating deep representations of graph structures like node2vec, Poincaré embeddings, GCN etc. that have recently demonstrated promising results on various NLP tasks. Furthermore, combining these representations with word embeddings allows us to beat the state of the art. We conduct a comprehensive study of the existing approaches to taxonomy enrichment based on word and graph vector representations and their fusion approaches. We also explore the ways of using deep learning architectures to extend the taxonomic backbones of knowledge graphs. We create a number of datasets for taxonomy extension for English and Russian. We achieve state-of-the-art results across different datasets and provide an in-depth error analysis of mistakes.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08598
PDF
-
SegTransVAE: Hybrid CNN -- Transformer with Regularization for medical image segmentation
2022-01-21 08:02:55Quan-Dung Pham (1), Hai Nguyen-Truong (1, 2 and 3), Nam Nguyen Phuong (1), Khoa N. A. Nguyen (1, 2 and 3) ((1) VinBrain JSC., Vietnam, (2) University of Science, Ho Chi Minh City, Vietnam, (3) Vietnam National University, Ho Chi Minh City, Vietnam)Abstract
Current research on deep learning for medical image segmentation exposes their limitations in learning either global semantic information or local contextual information. To tackle these issues, a novel network named SegTransVAE is proposed in this paper. SegTransVAE is built upon encoder-decoder architecture, exploiting transformer with the variational autoencoder (VAE) branch to the network to reconstruct the input images jointly with segmentation. To the best of our knowledge, this is the first method combining the success of CNN, transformer, and VAE. Evaluation on various recently introduced datasets shows that SegTransVAE outperforms previous methods in Dice Score and $95\%$-Haudorff Distance while having comparable inference time to a simple CNN-based architecture network. The source code is available at: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08582
PDF
-
Trustworthy Knowledge Graph Completion Based on Multi-sourced Noisy Data
2022-01-21 07:59:16Jiacheng Huang, Yao Zhao, Wei Hu, Zhen Ning, Qijin Chen, Xiaoxia Qiu, Chengfu Huo, Weijun RenAbstract
Knowledge graphs (KGs) have become a valuable asset for many AI applications. Although some KGs contain plenty of facts, they are widely acknowledged as incomplete. To address this issue, many KG completion methods are proposed. Among them, open KG completion methods leverage the Web to find missing facts. However, noisy data collected from diverse sources may damage the completion accuracy. In this paper, we propose a new trustworthy method that exploits facts for a KG based on multi-sourced noisy data and existing facts in the KG. Specifically, we introduce a graph neural network with a holistic scoring function to judge the plausibility of facts with various value types. We design value alignment networks to resolve the heterogeneity between values and map them to entities even outside the KG. Furthermore, we present a truth inference model that incorporates data source qualities into the fact scoring function, and design a semi-supervised learning way to infer the truths from heterogeneous values. We conduct extensive experiments to compare our method with the state-of-the-arts. The results show that our method achieves superior accuracy not only in completing missing facts but also in discovering new facts.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08580
PDF
-
Classroom Slide Narration System
2022-01-21 07:20:03Jobin K.V., Ajoy Mondal, C. V. JawaharAbstract
Slide presentations are an effective and efficient tool used by the teaching community for classroom communication. However, this teaching model can be challenging for blind and visually impaired (VI) students. The VI student required personal human assistance for understand the presented slide. This shortcoming motivates us to design a Classroom Slide Narration System (CSNS) that generates audio descriptions corresponding to the slide content. This problem poses as an image-to-markup language generation task. The initial step is to extract logical regions such as title, text, equation, figure, and table from the slide image. In the classroom slide images, the logical regions are distributed based on the location of the image. To utilize the location of the logical regions for slide image segmentation, we propose the architecture, Classroom Slide Segmentation Network (CSSN). The unique attributes of this architecture differs from most other semantic segmentation networks. Publicly available benchmark datasets such as WiSe and SPaSe are used to validate the performance of our segmentation architecture. We obtained 9.54 segmentation accuracy improvement in WiSe dataset. We extract content (information) from the slide using four well-established modules such as optical character recognition (OCR), figure classification, equation description, and table structure recognizer. With this information, we build a Classroom Slide Narration System (CSNS) to help VI students understand the slide content. The users have given better feedback on the quality output of the proposed CSNS in comparison to existing systems like Facebooks Automatic Alt-Text (AAT) and Tesseract.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08574
PDF
-
Identifying Adversarial Attacks on Text Classifiers
2022-01-21 06:16:04Zhouhang Xie, Jonathan Brophy, Adam Noack, Wencong You, Kalyani Asthana, Carter Perkins, Sabrina Reis, Sameer Singh, Daniel LowdAbstract
The landscape of adversarial attacks against text classifiers continues to grow, with new attacks developed every year and many of them available in standard toolkits, such as TextAttack and OpenAttack. In response, there is a growing body of work on robust learning, which reduces vulnerability to these attacks, though sometimes at a high cost in compute time or accuracy. In this paper, we take an alternate approach -- we attempt to understand the attacker by analyzing adversarial text to determine which methods were used to create it. Our first contribution is an extensive dataset for attack detection and labeling: 1.5~million attack instances, generated by twelve adversarial attacks targeting three classifiers trained on six source datasets for sentiment analysis and abuse detection in English. As our second contribution, we use this dataset to develop and benchmark a number of classifiers for attack identification -- determining if a given text has been adversarially manipulated and by which attack. As a third contribution, we demonstrate the effectiveness of three classes of features for these tasks: text properties, capturing content and presentation of text; language model properties, determining which tokens are more or less probable throughout the input; and target model properties, representing how the text classifier is influenced by the attack, including internal node activations. Overall, this represents a first step towards forensics for adversarial attacks against text classifiers.
Abstract (translated)
URL
https://arxiv.org/abs/2201.08555
PDF
