成人小说亚洲一区二区三区,亚洲国产精品一区二区三区,国产精品成人精品久久久,久久综合一区二区三区,精品无码av一区二区,国产一级a毛一级a看免费视频,欧洲uv免费在线区一二区,亚洲国产欧美中日韩成人综合视频,国产熟女一区二区三区五月婷小说,亚洲一区波多野结衣在线

立即打開
人臉識別技術(shù)很厲害?用這一招即可騙過

人臉識別技術(shù)很厲害?用這一招即可騙過

Jeff John Roberts 2018年06月23日
在這個(gè)技術(shù)猖獗的時(shí)代,阻撓人臉識別系統(tǒng)運(yùn)作的反制措施,或許會受到很多人的歡迎。

人的臉型和指紋一樣具有明顯特征,所以越來越多的組織——從警察局到學(xué)校到沃爾瑪(Wal-Mart)——都在借助人臉識別軟件來甄別線上照片和真實(shí)場景中的人。

然而人臉識別技術(shù)也開始給個(gè)人隱私帶來很大的威脅,一些研究者開始探求反制措施,其中包括多倫多大學(xué)計(jì)算機(jī)工程系的學(xué)生喬伊·博斯。

博斯稱他開發(fā)了一種工具,可以在照片上傳到網(wǎng)絡(luò)前加入額外的元素,從而“打亂”人臉識別系統(tǒng)。用肉眼看,處理前后的照片沒有任何區(qū)別,但處理后的照片有隱藏了的特性,可以阻止檢測系統(tǒng)的運(yùn)行。

博斯說:“這一工具可以給人臉圖像添加特殊制作的雜質(zhì),用于干擾人臉識別軟件,就像Instagram(圖片和視頻分享社交軟件——譯注)的過濾器?!?

博斯告訴《財(cái)富》雜志,這個(gè)工具很快會以手機(jī)應(yīng)用或者瀏覽器插件的形式出現(xiàn),他也已經(jīng)在GitHub(提供軟件源代碼托管服務(wù)網(wǎng)站——譯注)的個(gè)人主頁上分享了底層代碼。

在這個(gè)技術(shù)猖獗的時(shí)代,阻撓人臉識別系統(tǒng)運(yùn)作的反制措施,或許會受到很多人的歡迎。

有些私企會動腦筋,比如抓住人們對校園槍擊案的焦慮,向校區(qū)推廣人臉檢測系統(tǒng),盡管懷疑人士批駁這種系統(tǒng)反而造成了“安全威脅”,而且也不能阻止校園槍擊案的再次發(fā)生。而據(jù)《福布斯》(Forbes)上周的報(bào)道,亞馬遜網(wǎng)絡(luò)服務(wù)( Amazon Web Services)正在向顧客售賣人臉識別技術(shù),價(jià)格竟低至10美元。

這樣一來,博斯所開發(fā)的工具,通過減少人臉檢測軟件所需的有效人臉數(shù)量,就能減緩人臉識別技術(shù)的大范圍使用。

不過博斯的工具是預(yù)防性的,對于那些已經(jīng)獲取真實(shí)人臉信息,或者使用探頭在真實(shí)世界監(jiān)控人們的公司,這一工具就無能為力了。博斯認(rèn)為,要預(yù)防此類的人臉識別,人們也可以使用一些技巧,比如帶特殊形狀的眼鏡以糊弄檢測系統(tǒng),甚至在臉上貼點(diǎn)小標(biāo)簽。

貓鼠游戲

目前博斯的工具只對某幾類的人臉識別軟件有效,說得具體點(diǎn),就是它能破壞那些訓(xùn)練模式(用于訓(xùn)練軟件所設(shè)置的機(jī)器學(xué)習(xí)數(shù)據(jù)庫)可公開獲取的軟件。

有些安全軟件公司銷售的人臉檢測系統(tǒng)使用公開的數(shù)據(jù)庫,而有些則不是,最有名的是Facebook, 他們擁有自主產(chǎn)權(quán)的人臉檢測系統(tǒng),博斯的工具對它就不能奏效。

博斯懷疑,F(xiàn)acebook可能是在綜合使用不同的人臉識別技術(shù),以對付各種反制措施,比如他所開發(fā)的工具。但博斯認(rèn)為他的人臉識別破壞軟件最終也能阻撓Facebook,從而開啟一場識別人臉技術(shù)的開發(fā)者和掩藏人臉技術(shù)的開發(fā)者之間的貓鼠游戲。

這也提出了一個(gè)問題,阻撓人臉識別的工具會不會被商業(yè)化。博斯說已有幾家風(fēng)投找過他,但他決定暫不參與,今年秋季他會繼續(xù)他在麥吉爾大學(xué)的博士生研究項(xiàng)目。(財(cái)富中文網(wǎng))

譯者:Hank?

The shape of your face is as distinct as your fingerprint. That’s why a growing number of organizations — from police forces to schools to Wal-Mart — are using facial recognition software to identify you in online photos and in real world locations.

But facial recognition technology is beginning to pose a major privacy threat, which has led researchers to explore ways to counteract it. One of them is Joey Bose, a computer engineering student at the University of Toronto.

Bose claims he has developed a tool to “break” facial recognition systems by adding extra elements to photos before they are uploaded to the Internet. The photos don’t look any different to the naked eye, but the hidden features thwart detection systems.

“It adds specially-crafted noise for the face images. It’s trained to attack facial recognition software,” he said. “Think of it as Instagram filter.”

Bose told Fortune the tool will soon be available as a phone app or plug-in for web browsers, and that he has shared the underlying code on his GitHub page.

This opportunity to thwart facial recognition will likely be welcome by many people at a time when the technology is becoming more pervasive.

Private companies, for instance, have seized on anxiety over school shootings to sell face-detection systems to school districts — even as skeptics pan this as “security theater” that’s unlikely to prevent more shootings. Meanwhile, Forbes last week reported that Amazon Web Services is selling facial recognition technology to all comers for as little as $10.

Bose’s could thus slow the spread of the technology by reducing the number of faces available to companies that make the detection software.

His tool, however, is only a pre-emptive measure and does not address situations where a company already has an image of someone’s face and uses a camera to detect them in the real world. In order to prevent this sort of recognition, Bose says, people can employ tactics like wearing glasses with special patterns that fool the detection mechanisms or even put small stickers on their face.

A Cat-and-Mouse Game

For now, Bose’s tool only works to thwart certain types of facial recognition software. Specifically, it can break the software if the training model — the machine learning data set used to train the software — is publicly available.

While a number of facial detection systems sold by security companies rely on these publicly available data sets, other companies, notably Facebook, have their own proprietary versions that Bose’s tool can’t defeat.

Bose suspects that Facebook uses an ensemble of different facial recognition techniques in order to overcome counter-measures, like the one he developed, to fool its software. But he predicts his facial recognition duping tool will eventually be able to thwart Facebook, and set off a cat-and-mouse game between developers seeking to detect faces and those seeking to disguise them.

This raises the question of whether companies will seek to commercialize tools that thwart facial recognition. Bose says he has already been approached by a number of venture capitalists, but that he’s decided to pass for now. Instead, he says he plans to continue his research in a PhD program at McGill University starting this fall.

掃碼打開財(cái)富Plus App
97在线观看视频资源| 国内精品久久人妻无码妲己| 天天狠天天透天天伊人| 美丽人妻无套中出中文字幕 | 亚洲中文无码h在线观看| 亚洲aⅴ永久无码一区二区三区| 无码亚洲成a人片在线观看无码| 亚洲精品一品区二品区三品区| 久久久久精品久久久久影院蜜桃| 九九re热久久久久精品| 日韩精品无码一区二区| 成全动漫视频在线观看免费播放| 国产日韩在线观看国产精品一区二区av片| 精品无码人妻一区二区三区品| 日韩乱码人妻无码系列中文字幕| 精品久久久无码人妻| 国产a级综合区毛片久久国产精品不卡| 免费无码婬片AAAA片直播表情| 亚洲av之男人的天堂网站 720P | 国产在线无码精品麻豆不卡| 亚洲中国久久精品无码| 日本熟妇熟色一本在线观看| 国产第一国产综合精品| 日本裸体熟妇一区二区欧美| 久久久久久夜精品精品免费| 樱花官网官方进入入口| 中文字幕在线高清男人的天堂| 亚洲欧美日韩综合二区在线麻豆| 国产精品一区二区 尿失禁| 无遮挡h纯内动漫在线观看| 国产乱子伦精品无码码专区| 香蕉久久夜色精品国产尤物| 影音先锋女人av鲁色资源网站| 久久夜噜噜噜亚洲AV蜜臀| 免费A级毛片无码免费视频| 亚洲国产成人精品电影| 久久精品亚洲无中文| 久久久久久精品人妻无码动漫专区| 国产精品高潮呻吟久久AV| 国产午夜片无码区在线播放| 久久久久久久亚洲AV无码|