基于交易時(shí)間衰減的以太坊惡意地址檢測(cè)方法
網(wǎng)絡(luò)安全與數(shù)據(jù)治理
梁飛1,石文君2,蘇則燊3,張敏4
1.北京市公安局經(jīng)濟(jì)犯罪偵查總隊(duì);2.北京市公安局海淀分局; 3.華中科技大學(xué);4.北京市公安局網(wǎng)絡(luò)安全保衛(wèi)總隊(duì)
摘要: 提出Trans-TAN模型,用于以太坊上的交易流向圖中關(guān)聯(lián)惡意地址的檢測(cè)任務(wù),模型改進(jìn)基于Transformer模型的自注意力機(jī)制,根據(jù)以太坊地址的交易特點(diǎn)并受到牛頓冷卻定理的啟發(fā),引入隨時(shí)間交易的時(shí)間間隔衰減因素,同時(shí)融合以太坊地址間的相似度因素和交易金額因素。基于以上三方面,通過牛頓冷卻定理的常微分方程解形式構(gòu)建的地址關(guān)聯(lián)矩陣,從而改進(jìn)原有的自注意力矩陣。實(shí)驗(yàn)證明,Trans-TAN模型能夠有效捕捉以太坊交易流向圖過程中惡意節(jié)點(diǎn)地址的特征,在測(cè)試集中精準(zhǔn)率 (Precision)、召回率(Recall)和F1指標(biāo)優(yōu)于傳統(tǒng)的檢測(cè)模型。
中圖分類號(hào):TP311.13;TP309;TP183文獻(xiàn)標(biāo)識(shí)碼:ADOI:10.19358/j.issn.2097-1788.2024.07.005
引用格式:梁飛,石文君,蘇則燊,等.基于交易時(shí)間衰減的以太坊惡意地址檢測(cè)方法[J].網(wǎng)絡(luò)安全與數(shù)據(jù)治理,2024,43(7):26-31.
引用格式:梁飛,石文君,蘇則燊,等.基于交易時(shí)間衰減的以太坊惡意地址檢測(cè)方法[J].網(wǎng)絡(luò)安全與數(shù)據(jù)治理,2024,43(7):26-31.
Ethereum malicious address detection method based on transaction time decay
Liang Fei1,Shi Wenjun2,Su Zeshen3 ,Zhang Min4
1. Economic Crime Investigation Brigade of Beijing Municipal Public Security Bureau; 2. Haidian Branch of Beijing Municipal Public Security Bureau; 3. Huazhong University of Science and Technology; 4. Beijing Municipal Public Security Bureau Network Security Corps
Abstract: This article proposes the Trans-TAN model for detecting malicious addresses associated with transaction flow graphs on Ethereum. The model improves the self attention mechanism based on the Transformer model. Inspired by Newton′s cooling theorem and based on the transaction characteristics of Ethereum addresses, the Trans-TAN model introduces the time decay factor of transaction intervals over time. At the same time, it integrates the similarity factor between Ethereum addresses and the transaction amount factor. Based on the above three factors, the address association matrix is constructed in the form of a solution to the ordinary differential equation of Newton′s cooling theorem, thereby improving the original self attention matrix. Experimental results show that the Trans-TAN model can effectively capture the characteristics of malicious node addresses in the Ethereum transaction flow graph process, and its accuracy in the test set (Pre) is improved. The precision, recall, and F1 metrics are superior to traditional detection models.
Key words : Ethereum account; Newton′s cooling theorem; time interval decay; self attention mechanism
引言
近年來利用虛擬貨幣為媒介的犯罪日趨猖獗,傳統(tǒng)的網(wǎng)絡(luò)賭博、網(wǎng)絡(luò)黑灰產(chǎn)、洗錢[1]等正在借助虛擬貨幣匿名性和去中心化的特點(diǎn)實(shí)現(xiàn)支付結(jié)算。同時(shí)利用虛擬貨幣從事網(wǎng)絡(luò)賭博、詐騙、傳銷類、洗錢類、黑灰產(chǎn)類的案件呈高發(fā)態(tài)勢(shì),例如在2023年底北京市經(jīng)偵總隊(duì)破獲了北京市首例利用虛擬貨幣從事非法換匯案件,嫌疑人利用虛擬貨幣為境內(nèi)人員換匯金額高達(dá)10億元,嚴(yán)重?cái)_亂金融秩序,因此建立以技術(shù)手段為基礎(chǔ)從而阻斷使用虛擬貨幣淪為犯罪工具顯得迫在眉睫。
本文詳細(xì)內(nèi)容請(qǐng)下載:
http://theprogrammingfactory.com/resource/share/2000006088
作者信息:
梁飛1,石文君2,蘇則燊3,張敏4
(1.北京市公安局經(jīng)濟(jì)犯罪偵查總隊(duì),北京100062;
2.北京市公安局海淀分局,北京100086;
3.華中科技大學(xué),湖北武漢430074;
4.北京市公安局網(wǎng)絡(luò)安全保衛(wèi)總隊(duì),北京100081)
此內(nèi)容為AET網(wǎng)站原創(chuàng),未經(jīng)授權(quán)禁止轉(zhuǎn)載。