首页/论文/2012.11775

arXiv 2012.117752020-12-22cs.LGcs.CR

MailLeak: Obfuscation-Robust Character Extraction Using Transfer Learning

University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Ohio State University（俄亥俄州立大学）

Wei Wang, Emily Sallenback, Zeyu Ning, Hugues Nelson Iradukunda, Wenxi Lu, Qingquan Zhang, Ting Zhu

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

The following work presents a new algorithm for character recognition from obfuscated images. The presented method is an example of a potential threat to current postal services. This paper both analyzes the efficiency of the given algorithm and suggests countermeasures to prevent such threats from occurring.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

大型语言模型的提示混淆

Prompt Obfuscation for Large Language Models

CISPA Helmholtz Center for Information Security（CISPA 德国信息安全中心）；Berlin Institute for the Foundations of Learning and Data (BIFOLD)（柏林学习与数据基础研究所）；Technische Universität Berlin（柏林技术大学）

本文提出提示混淆方法，通过生成功能相同但不含原始信息的混淆提示，防止系统提示被提取，实验证明其有效保护知识产权且保持同等效用。

2025-08-06cs.CRcs.LG

DeepObfusCode: Source Code Obfuscation Through Sequence-to-Sequence Networks

Hong Kong University of Science and Technology（香港科技大学）

The paper explores a novel methodology in source code obfuscation through the application of text-based recurrent neural network (RNN) encoder-decoder models in ciphertext generation and key generation. Sequence-to-sequence models are incorporated into the model architecture to generate obfuscated code, generate the deobfuscation key, and live execution. Quantitative benchmark comparison to existing obfuscation methods indicate significant improvement in stealth and execution cost for the proposed solution, and experiments regarding the model's properties yield positive results regarding its c…

2021-02-25cs.CRcs.LGcs.SE

通过二进制代码的基于图的语义分析识别混淆代码

Identifying Obfuscated Code through Graph-Based Semantic Analysis of Binary Code

Quarkslab（夸克实验室）；LAMSADE（LAMSADE实验室）；CNRS（法国国家科学研究中心）；Université Paris-Dauphine - PSL（巴黎多芬大学-巴黎文理研究大学）；LITIS（LITIS实验室）；INSA Rouen Normandy（鲁昂诺曼底国立应用科学学院）；CEREMADE（CEREMADE实验室）

本文研究函数级混淆检测问题，使用基于图的方法比较了从基线到GNN的多种算法，发现GNN需结合捕获函数语义的特征才能优于基线，并在11类分类和恶意软件分析中取得满意结果。

2025-04-02cs.CRcs.LGstat.ML

NeuroUnlock: Unlocking the Architecture of Obfuscated Deep Neural Networks

Technische Universität Wien（维也纳工业大学）；New York University Abu Dhabi（纽约大学阿布扎比分校）

The advancements of deep neural networks (DNNs) have led to their deployment in diverse settings, including safety and security-critical applications. As a result, the characteristics of these models have become sensitive intellectual properties that require protection from malicious users. Extracting the architecture of a DNN through leaky side-channels (e.g., memory access) allows adversaries to (i) clone the model, and (ii) craft adversarial attacks. DNN obfuscation thwarts side-channel-based architecture stealing (SCAS) attacks by altering the run-time traces of a given DNN while preservin…

2022-06-01cs.CRcs.LG

超越黑盒混淆：白盒监测器的机制分析与防御

Beyond Black-Box Obfuscation: Mechanistic Analysis and Defense of White-Box Monitors

University of Oxford（牛津大学）

研究针对大语言模型白盒监测器可被规避且缺乏防御措施的问题，通过红队实验揭示几何转移和协方差操纵两种逃避策略，引入SafetyNet集成方法，在多模型家族实验中取得高AUROC分数，为稳健潜在空间监测提供了实证和起点。

2026-07-13cs.AIcs.CLcs.LG

Information Extraction with Character-level Neural Networks and Free Noisy Supervision

Bloomberg LP（彭博有限合伙企业）；AT&T Labs Research（AT&T实验室研究部）

We present an architecture for information extraction from text that augments an existing parser with a character-level neural network. The network is trained using a measure of consistency of extracted data with existing databases as a form of noisy supervision. Our architecture combines the ability of constraint-based information extraction systems to easily incorporate domain knowledge and constraints with the ability of deep neural networks to leverage large amounts of data to learn complex features. Boosting the existing parser's precision, the system led to large improvements over a matu…

2017-01-24cs.CLcs.IRcs.LG

更多相关论文收起更多论文

Discriminative Autoencoder for Feature Extraction: Application to Character Recognition

Indraprastha Institute of Information Technology（因德拉普拉斯信息技术学院）

Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to variations commonly encountered in image datasets. Using the basic discriminating autoencoder as a unit, we build a stacked architecture aimed at extracting relevant representation from the training data. The efficiency of our feature extraction algorithm ensures a high classification accuracy with even simple classification schemes like KNN (K-nearest neighbor). W…

2019-12-11cs.CVcs.LG

End-to-End Information Extraction by Character-Level Embedding and Multi-Stage Attentional U-Net

Cinnamon AI Labs（肉桂人工智能实验室）

Information extraction from document images has received a lot of attention recently, due to the need for digitizing a large volume of unstructured documents such as invoices, receipts, bank transfers, etc. In this paper, we propose a novel deep learning architecture for end-to-end information extraction on the 2D character-grid embedding of the document, namely the \textit{Multi-Stage Attentional U-Net}. To effectively capture the textual and spatial relations between 2D elements, our model leverages a specialized multi-stage encoder-decoders design, in conjunction with efficient uses of the …

2021-09-09cs.CVcs.LGeess.IV

A Gaussian Process Upsampling Model for Improvements in Optical Character Recognition

University of California, Santa Cruz（加州大学圣克鲁兹分校）；AppZen Inc.（AppZen公司）

Optical Character Recognition and extraction is a key tool in the automatic evaluation of documents in a financial context. However, the image data provided to automated systems can have unreliable quality, and can be inherently low-resolution or downsampled and compressed by a transmitting program. In this paper, we illustrate the efficacy of a Gaussian Process upsampling model for the purposes of improving OCR and extraction through upsampling low resolution documents.

2020-05-07cs.CVcs.LGstat.ML

基于角色的服装生成：通过 LLMs 进行视觉增强的风格提取

Character-based Outfit Generation with Vision-augmented Style Extraction via LLMs

Walmart Global Tech（沃尔玛全球科技）

本文提出了基于角色的服装生成（COG）问题及框架 LVA-COG，利用 LLMs 提取角色兴趣并采用提示工程理解偏好，结合文本到图像模型增强视觉理解与生成，实现个性化服装推荐。

2024-02-02cs.AIcs.CVcs.IR