報(bào)告題目：Adversarial Machine Learning for Network Security
報(bào)告人：石怡 首席研究員
單位：美國(guó)智能自動(dòng)化公司/美國(guó)弗吉利亞理工大學(xué)
報(bào)告時(shí)間：2019年11月29日（周五）下午3點(diǎn)
報(bào)告地點(diǎn)：翡翠科教樓A座1104會(huì)議室
摘要：With the rapid growth of machine learning applications in communication networks, it is essential to understand the security issues associated with machine learning. In this talk, we choose a slow-based Deep Neural Network (DNN) classifier as a target and study various attacks on this target classifier. The target classifier detects malicious HTTP traffic (i.e., bots, C&C, etc.). We first launch an exploratory attack under a black box assumption against the target CNN classifier. We start from a simple case that the attacker can collect the same set of features used in the target classifier and then consider the case that the attacker can only collect a set of features based on its judgement. We also design the attacks with conditional Generative Adversarial Network (cGAN) to reduce the requirement on the amount of collected data. We show that the attacker can build its own classifier to predict the target classifier's classification results with about 93% accuracy. Once the exploratory attack is successful, we can perform further attacks, e.g., evasion attack and causative attack. We show that these attacks are very effective. Evasion atack can identify samples to double error probability of the target classifier while under causative attack, the new classifier makes classification errors on more than 60% of samples.
報(bào)告人簡(jiǎn)介：
石怡，1998年畢業(yè)于中國(guó)科技大學(xué)零零班獲取學(xué)士學(xué)位，2001年畢業(yè)于中科院軟件所（現(xiàn)中科院大學(xué)）獲取碩士學(xué)位，2003年畢業(yè)于美國(guó)弗吉利亞理工大學(xué)獲取第二個(gè)碩士學(xué)位，2007年畢業(yè)于美國(guó)弗吉利亞理工大學(xué)獲取博士學(xué)位?，F(xiàn)為IEEE高級(jí)會(huì)員，美國(guó)智能自動(dòng)化公司首席研究員，美國(guó)弗吉利亞理工大學(xué)兼職教授。石怡博士是國(guó)際上知名的無(wú)線網(wǎng)絡(luò)優(yōu)化專家，已經(jīng)在IEEE Transactions on Mobile Computing等著名期刊上和IEEE INFOCOM等著名會(huì)議上發(fā)表論文150多篇，并主編出版專著1部，參與編寫專著5部。2006年，石博士以華盛頓區(qū)第一名的身份獲得由中國(guó)政府頒發(fā)的“國(guó)家優(yōu)秀自費(fèi)留學(xué)生”的獎(jiǎng)勵(lì)；2008年和2011年，石博士的論文先后兩次在IEEE INFOCOM會(huì)議中獲得最佳論文獎(jiǎng)及最佳論文入圍獎(jiǎng)。石博士擔(dān)任IEEE Communications Surveys and Tutorials編輯，擔(dān)任過(guò)3個(gè)workshop的技術(shù)委員會(huì)主席和近50個(gè)國(guó)際會(huì)議的技術(shù)委員會(huì)委員，包括IEEE INFOCOM, ACM MobiHoc, IEEE MILCOM, IEEE ICC, IEEE WCNC, IEEE GLOBECOM等。
TOP
