• Journal of Electrical Engineering and Technology
• /
• 제10권1호
• /
• pp.401-407
• /
• 2015

The increase of image spam, a kind of spam in which the text message is embedded into attached image to defeat spam filtering technique, is a major problem of the current e-mail system. For nearly a decade, content based filtering using text classification or machine learning has been a major trend of anti-spam filtering system. Recently, spammers try to defeat anti-spam filter by many techniques. Text embedding into attached image is one of them. We proposed an ontology spam filters. However, the proposed system handles only text e-mail and the percentage of attached images is increasing sharply. The contribution of the paper is that we add image e-mail handling capability into the anti-spam filtering system keeping the advantages of the previous text based spam e-mail filtering system. Also, the proposed system gives a low false negative value, which means that user's valuable e-mail is rarely regarded as a spam e-mail.

• International Journal of Advanced Culture Technology
• /
• 제5권1호
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권2호
• /
• pp.105-109
• /
• 2006

In this paper, we constructed a two-phase spam-mail filtering system based on the lexical and conceptual information. There are two kinds of information that can distinguish the spam mail from the ham (non-spam) mail. The definite information is the mail sender's information, URL, a certain spam keyword list, and the less definite information is the word list and concept codes extracted from the mail body. We first classified the spam mail by using the definite information, and then used the less definite information. We used the lexical information and concept codes contained in the email body for SVM learning in the 2nd phase. According to our results the ham misclassification rate was reduced if more lexical information was used as features, and the spam misclassification rate was reduced when the concept codes were included in features as well.

• 한국IT서비스학회지
• /
• 제13권3호
• /
• pp.299-308
• /
• 2014

Due to indiscriminately received spam messages on information society, spam messages cause damages not only to person but also to our community. Nowadays a lot of spam filtering techniques, such as blocking characters, are studied actively. Most of these studies are content-based spam filtering technologies through machine learning.. Because of a spam message transmission techniques are being developed, spammers have to send spam messages using term spamming techniques. Spam messages tend to include number of nouns, using repeated words and inserting special characters between words in a sentence. In this paper, considering three features, SPSS statistical program were used in parameterization and we derive the equation. And then, based on this equation we measured the performance of classification of spam messages. The study compared with previous studies FP-rate in terms of further minimizing the cost of product was confirmed to show an excellent performance.

• 전자공학회논문지CI
• /
• 제48권6호
• /
• pp.123-139
• /
• 2011

웹 스팸은 중요하지 않은 웹 페이지들의 중요도를 승격시키기 때문에 웹 검색 결과의 품질에 중대한 영향을 준다. 따라서 웹 검색 엔진은 웹 스팸을 제거할 필요가 있다. 웹 스팸 필터링은 스팸 페이지들, 즉 웹 스팸에 기여하는 웹 페이지들을 식별하는 것이며, 잘 알려진 웹 스팸 필터링 알고리즘으로는 Trust Rank, Anti-Trust Rank, Spam Mass, 그리고 Link Farm Spam이 있다. 이러한 알고리즘들의 결과 품질은 입력 시드(input seed)에 따라 달라진다. 따라서 입력 시드를 정제(refinement) 함으로써, 웹 스팸 필터링의 품질을 향상 시킬 수 있다. 본 논문에서는 잘 알려진 네 가지 알고리즘에 대한 시드를 정제하는 기술을 제안한다. 다음으로, 이러한 기술을 원(original) 알고리즘에 각각 적용하는 방법으로 알고리즘을 수정한다. 이를 수정된 웹 스팸 필터링 알고리즘이라고 부른다. 본 논문에서는 또한, 웹 스팸 필터링을 좀 더 향상시키기 위한 전략을 제안한다. 이 전략에서는 수정된 알고리즘들을 수행 순서상의 적절한 위치에 배치함으로써 알고리즘들의 상호간 지원을 통해 전체적으로 성능을 향상시키는 가능성을 고려한다. 마지막으로, 실험에서는 시드 정제의 효과를 보인다. 이를 위해, 먼저, 수정된 알고리즘의 웹 스팸 필터링 품질이 원 알고리즘의 품질보다 더 우수함을 보인다. 다음으로, 웹 스팸 필터링 알고리즘들이 수행되는 순서의 조합 중 가장 성능이 우수한 조합이 가장 뛰어난 잘 알려진 알고리즘과 비교하여 정확도(precision)를 유지하면서 파라미터의 전형적인 값 범위 내에서 재현율(recall)은 최대 1.38배까지 높게 향상됨을 보인다.

• 대한산업공학회지
• /
• 제43권3호
• /
• pp.192-202
• /
• 2017

This study develops a text spam filtering system for Facebook based on two variable categories: keywords learned from Instagram and meta-information of Facebook posts. Since there is no explicit labels for spam/ham posts, we utilize hash tags in Instagram to train classification models. In addition, the filtering accuracy is enhanced by considering meta-information of Facebook posts. To verify the proposed filtering system, we conduct an empirical experiment based on a total of 1,795,067 and 761,861 Facebook and Instagram documents, respectively. Employing random forest as a base classification algorithm, experimental result shows that the proposed filtering system yield 99% and 98% in terms of filtering accuracy and F1-measure, respectively. We expect that the proposed filtering scheme can be applied other web services suffering from massive spam posts but no explicit spam labels are available.

• 정보처리학회논문지C
• /
• 제13C권2호
• /
• pp.259-266
• /
• 2006

스팸 메일의 양의 급증함에 따라, 다양한 스팸 메일 필터링 기법이 제시되고 있다. 이런 필터링 기법 가운데, 학습 기반 필터링 기법은 현재 가장 보편화된 필터링 기법 가운데 하나이다. 본고에서는 신경망과, 유전자알고리즘, 카이제곱통계를 이용한 학습 기반 필터링 기법을 제시한다. 제안된 필터링 기법은 기존 필터링 기법의 문제를 해결하고, 스팸 메일 필터링에 높은 정확도를 제공할 수 있다 제안된 필터링 기법은 스팸메일 필터링 정확도와 정상 메일 필터링 정확도에서 각각 95.25%와 95.31%의 높은 정확도를 보인다. 이런 실험 결과는 기존의 규칙 기반 필터링 기법과 베이지안 필터링 기법에 비해 각각 7%, 12% 이상 높은 수치이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권2호
• /
• pp.604-625
• /
• 2018

Nowadays, SMS spam has been overflowing in many countries. In fact, the standards of filtering SMS spam are different from country to country. However, the current technologies and researches about SMS spam filtering all focus on dividing SMS message into two classes: legitimate and illegitimate. It does not conform to the actual situation and need. Furthermore, they are facing several difficulties, such as: (1) High quality and large-scale SMS spam corpus is very scarce, fine categorized SMS spam corpus is even none at all. This seriously handicaps the researchers' studies. (2) The limited length of SMS messages lead to lack of enough features. These factors seriously degrade the performance of the traditional classifiers (such as SVM, K-NN, and Bayes). In this paper, we present a new fine categorized SMS spam corpus which is unique and the largest one as far as we know. In addition, we propose a classifier, which is based on the probability topic model. The classifier can alleviate feature sparse problem in the task of SMS spam filtering. Moreover, we compare the approach with three typical classifiers on the new SMS spam corpus. The experimental results show that the proposed approach is more effective for the task of SMS spam filtering.

• 한국정보기술응용학회:학술대회논문집
• /
• 한국정보기술응용학회 2005년도 6th 2005 International Conference on Computers, Communications and System
• /
• pp.21-25
• /
• 2005

In this paper, we constructed a two-phase spam-mail filtering system based on the lexical and conceptual information. There are two kinds of information that can distinguish the spam mail from the legitimate mail. The definite information is the mail sender's information, URL, a certain spam list, and the less definite information is the word list and concept codes extracted from the mail body. We first classified the spam mail by using the definite information, and then used the less definite information. We used the lexical information and concept codes contained in the email body for SVM learning in the $2^{nd}$ phase. According to our results the spam precision was increased if more lexical information was used as features, and the spam recall was increased when the concept codes were included in features as well.

• 전기전자학회논문지
• /
• 제10권1호
• /
• pp.49-54
• /
• 2006

최근 전자 우편은 IT 사회의 중요한 의사소통의 수단이 되고 있다. 그러나 스팸 메일의 증가로 인해 다양한 사회 문제가 발생되고 증가하는 추세이다. 스팸 메일을 차단하기 위해 정부와 민간 단체에서 많은 연구와 개발을 하고 있으나 다양한 스팸 메일의 증가로 인해 많은 비용과 시스템의 복잡성이 요구되어 지고 있다. 이러한 문제점을 해결하기 위해 본 논문에서는 Fit-FA Finder를 이용한 SMBC(Spam Mail Blocking Center)를 설계 하였다. Fit-FA Finder는 스팸 메일의 유형에 따라 필터링 데이터베이스에서 적절한 알고리즘을 적용 시키는 시스템으로서 필터의 적용 순서에 따라 스팸 메일 오인율(False-Positive Error)이 달라져 시스템 처리 신뢰도에 큰 영향을 준다. 본 논문에서 제안한 Fit-FA Finder를 이용한 SMBC 플랫폼은 불필요한 필터링 처리 과정을 줄임으로써 시스템의 부하를 줄 일수 있다.