در تنسورفلو هاب داشتم گشت میزدم به یه ماژول جالبی برخورد کردم. گفتم به اشتراک بگذارم .
https://www.tensorflow.org/tutorials/image_retraining
ماژولی به نام retrain که میتونه برای #یادگیری_انتقالی (استفاده از مدل آموزش داده شده برای ایجاد مدل ای جدید) استفاده بشه و از دیتاست محدودی که بهش داده میشه کلاس جدید استخراج (ایجاد) کنه.
برای اطلاعات بیشتر لینک زیر جالب توجه است:
https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0

Real-World Robot Learning (TensorFlow Dev Summit 2018)

توسعه دهندگان تنسور فلو

#پیشنهاد
مقاله ای میخوندم در مورد امنیت صحت خروجی DNN
بنام One pixel attack for fooling deep neural networks
(البته برای یه ماه و نیم پیشه احتمالا اساتید دیده باشن)
https://arxiv.org/abs/1710.08864
ایده مقاله اینه که با علم به اینکه تغییر دادن یه مقدار خاصی از داده تست (تصویر RGB) میتونه باعث شه که CNN گول بخوره و نتونه درست دسته بندی کنه، چطور میتونیم به حداقل تعداد تغییر در پیکسل برسیم که باعث بشیم CNN اشتباه کنه. اومدن کلاس های احتمالی ای که CNN پیشنهاد داده رو نگاه کردن، با استفاده از یه الگوریتمی بنام دیفرانسیل تکاملی یکسری عکس رندوم (تو داده تست) که هربار یه تغییری رندوم تو تصویر میده رو ایجاد کردن و فید کردن به CNN. اگه صحت رو کاهش داد جایگزین میشه با داده تست قبلی. و این فرایند تکاملی وار ادامه پیدا پیدا میکنه تا صحت (accuracy) کمینه بشه و در عین حال از تغییرات پیکسلی کمتری استفاده بشه.
خود Differential evolution برای من تازگی داشت و دارم در موردش میخونم.
—---------------------------------------------------------------------------------------—
اخیرا پیاده سازی خیلی خوبی برای این مقاله تو گیت هاب دیدم در لینک زیر
https://github.com/Hyperparticle/one-pixel-attack-keras
با استفاده از keras روی cifar10 پیاده سازی شده.
اومده برای معماری های رایج با اسفاده از تغییر دادن یک پیکسل، سه پیکسل و پنج پیکسل حمله رو انجام داده و میزان صحت اون کلاس غلط رو گزارش کرده. تو ریپازیتوری نسخه pretrain شده LeNet و ResNet هست.
برای دانلود بقیه معماری ها (که حجیم ان) از لینک زیر:
https://www.dropbox.com/sh/dvatkpjl0sn79kn/AAC9L4puJ_sdFUkDZfr5SFkLa?dl=0
و قرار دادنشون تو پوشه models
—-------------------------------------------------------------------------------------
کارهای بیشتر
روی حمله هدف گذاری شده اش پیاده سازی کاملی انجام گرفته. توی هر تکرار میاد میزان صحت دسته بندی کلاسی که میخواد به قصد CNN رو مجبور به غلط دسته بندی کردنش داره رو نیگاه میکنه و با DE سعی در کمینه کردن اش داره. اما یه قسمتی هم داره که untargeted attack هست. روی اون میشه کار کرد. یعنی عکس لاک پشت رو دادیم. مهم نیست با چه label ای غلط دسته بندی کنه، فقط میخوایم اشتباه کنه. متد ای داره ژوپیتر نوت بوک اش بنام attck که داخل اش میشه از الگوریتم جدیدی برای هوشمندتر کردنش استفاده کرد.

نتایجش بسیار جالبه. کمترین میزان تاثیر رو روی شبکه های کپسولی داشته.

#خبر و چالش
توجه ویژه مسترکارت به سیستم سکوریتی و پسورد کارت های مبتنی بر بیومتریک و هوش مصنوعی


In financial services today, security and innovation can work with each other, and against each other.

FinServ cybersecurity is, of course, a prime target for innovation. But customers’ constant demand for cutting-edge products and services is adding to the load of already heavy security burdens. At the same time, providers must ensure a positive, consistent customer experience.

Mastercard Chief Security Solutions Officer Ajay Bhalla recently explored the relationship between financial services innovation and security, telling PYMNTS how these two dynamics can complement each other while guiding the FinServ space in its journey to a better service offering.

Bank customers’ needs and demands of financial service providers are growing more sophisticated and complex. What is driving this trend?

According to the Digital Evolution Index, more countries in more parts of the world have robust digital ecosystems, driving demand for trusted technology. We are on track toward a world with more than 30 billion connected devices – an irreversible trend that is dramatically changing the digital economy and delivering fulfillment of the possibility that consumers have been waiting for: The ability to increase transparency, interact with brands and move faster, with less friction.

For the banks and merchants serving them, the challenge is matching the great strides in connectivity with consistency of experience and security. The pace of innovation focused on consumer experience is showing no signs of slowing down. Meanwhile, criminals are increasingly using technology designed for good in a nefarious manner. Key to success in 2018 will be the adoption of a security by design approach in innovation that marries the establishment and deployment of standards with leading edge technology.

With so many options available to financial service providers to implement and offer new technologies, how can they provide a consistent end-user experience while ensuring that products and services are cutting-edge?

We’re off to a great start in 2018, securing innovation through globally adopted standards like 3-D Secure 2.0 from EMVCo and “PIN on Glass” from the PCI Council. These create consistency and pave the way for banks and merchants to plug in and leverage the power of billions of connected devices to deliver greater consumer experiences, while also addressing threats from cyberattacks and hacks. Put simply: Industry standards enable trust and make it feasible to scale the use of technology.

Passwords remain commonplace, despite the evolution of security technology. How can financial service providers address customer demand for authentication processes that are more secure, efficient and convenient than passwords?

For consumers – some of which have up to 90 online accounts and find passwords difficult to remember – we have room to improve. For the past five years, we’ve been very focused on getting rid of passwords. Passwords are “something you know,” not “something you are.” Remembering passwords is frustrating, and only getting harder as digital activities proliferate. Identifying people by who they are makes life safer and simpler for the individual.

That is the driving force behind our efforts to develop Identity Check, which uses biometric identifiers, such as fingerprint, iris, facial or voice, to verify consumers’ identities using a mobile device during online shopping and banking activities. This speeds up checkout time, improves security and reduces cart abandonment rates. Our biometric payment card, which has already been trialed with consumers, is another example of reshaping their experience. And by retaining focus on consumer-centric solutions, we are not restricted to the single biometric of any device.

These technologies are on the edge of innovation, and research we conducted in partnership with the University of Oxford found that 92 percent of banking professionals want to adopt biometric technology. 2

018 is the year we can scale the adoption of biometrics in payments.

Artificial intelligence is another technology that’s driving advancement of financial service cybersecurity. How will FinServ players deploy AI tools in the coming year?

Artificial intelligence and machine learning are increasingly providing the means to interpret and action the complexity and scale of data to generate useful intelligence and an individualized outcome for every interaction, despite the scale/volume. For us, artificial intelligence is already embedded in our network and how we help protect our partners. The acquisition of Brighterion progressed our use of AI, enabling our network to adapt faster and deliver even greater accuracy in decisioning and managing risk.

AI is increasingly being deployed to help banks and merchants look at these new data points to give people a better experience. This will continue to grow in 2018, but the shift will be focused on leveraging the Internet of Things through behavioral analytics. Our acquisition of NuData Security has improved visibility into what is happening at the device level. It allows us to assess patterns of behavior of the user, detect botnet automation and determine the reputation of the device – critical insight for merchants in optimizing the consumer experience and for issuers in determining whether to approve payment. This capability can be applied across any device in the future.

What barriers will the financial services space have to overcome as it integrates and experiments with new technologies to enhance both the customer experience and security?

The internet holds the promise of a bright future ahead, but between here and there is a chasm – and it’s called insecurity. The investment in technology, such as physical biometrics, advanced behavioral analytics, risk-based authentication and artificial intelligence, will grow. It has to, in order to secure digital payments, mobile banking applications and other channels across established, challenger and FinTech sectors. Securing innovation and innovating security will help get us across the chasm and deliver greater trust in the right technologies in 2018.

منبع:
https://www.pymnts.com/news/b2b-payments/2018/mastercard-finserv-innovation-security-ai-b2b/

20 مقاله ی برتر یادگیری عمیق
Top 20 #DeepLearning Papers, 2018 Edition http://goo.gl/ScbfwP

از طرف خانم دکتر مهرنوش

#پیشنهاد
قابل توجه علاقه مندان به NLP
لینک زیر مجموعه گزارش های دانشجویان دانشگاه استنفورد در مورد دوره زیر است:
Natural Language Processing with Deep Learning
با محوریت کار بر روی دیتاست پرسش و پاسخ کوتاه خود استنفورد (SQuAD)
گزارش کار آقای شریف زاده رو هم بخونین. مقدمه اش جالبه😂
http://web.stanford.edu/class/cs224n/reports.html

برای دوستانی که به برنامه نویسی با موبایل علاقه مند هستند تنسورفلو یاری ردیف کرده

https://github.com/benoitsteiner/tensorflow-opencl

برای گوشی های اندرویدی که جی پی یو خوبی دارن میتونه جالب باشه👆

با تشکر از دوست عزیز
@AlcatrazJG

وبینار آینده بیومتریک روی موبایل

WEBINAR RECORDING: New Frontiers in Mobile Biometrics

Posted on March 29, 2018



Hot on the heels of Mobile World Congress 2018 in Barcelona, FindBiometrics and GSMA hosted the mobile biometrics webinar event of the year: New Frontiers in Mobile Biometrics. The 45 minute webcast began with a review of the biggest identity tech news out of MWC and a presentation from GSMA’s David Pollington highlighting the state of global mobile identity initiatives. The conversation then opened to include industry thought leaders Frances Zelazny, VP, BioCatch, and Fredrik Clementson, R&D Director, Precise Biometrics, for an expert panel discussion that provided insight into key biometrics topics such as:

– How new regulations like PSD2 are affecting the mobile identity management industry
– What’s next for mobile biometrics now that strong authentication is ubiquitous in the smartphone market
– How new innovations in smart cards, AI and connectivity are making biometrics essential to the mobile-first world of consumer finance
– What role standards and specifications bodies play in the new mobile biometrics landscape
– How world leading biometrics vendors are addressing emerging challenges in this dynamic market
در ادامه فیلم مربوط به این وبینار گذاشته خواهد شد.
منبع:
https://findbiometrics.com/webinar-new-frontiers-mobile-biometrics-503299/

دوستان گلم سلام و عرض ادب یکی از بچه های خوب گروهی، که ایشون در امریکا به سر می برن این متن رو گذاشتن و با اجازه ایشون در اینجا به اشتراک می گذارم....
"
سلام دوستان. بچه های امنیتی نگاهی به برنامه کاراموزی لب ما بندازید. دانجشو میگیریم. اطلاعات کامل.

http://sefcom.asu.edu/internship.html

فقط فرمودند که ای دی اشان رو اشتراک نگذارم و فقط جهت اگاهی شما اعلام نموندند..... امیدوارم شما دوستان عزیز یکی از کسانی باشید که موفق به اپلای در این زمینه باشید. با تشکر از محسن عزیز.

اگر کسی از دوستان تونستن پذیرش اولیه بگیرن حتما بنده رو در جریان بگذارید که شما رو بتونم با آقا محسن عزیز در اون تایم لینک کنم که کمک بیشتر برایتان شود. 🙏🙏🙏

ویدیومربوط به این وبینار

یک تعریف و تکفیک خوب بین داده کاوی و مهندس یدانش و یادگیری ماشین.
Difference of Data Science, Machine Learning and Data Mining
Data is almost everywhere. The amount of digital data that currently exists is now growing at a rapid pace. The number is doubling every two years and it is completely transforming our basic mode of existence. According to a paper from IBM, about 2.5 billion gigabytes of data had been generated on a daily basis in the year 2012. Another article from Forbes informs us that data is growing at a pace which is faster than ever. The same article suggests that by the year 2020, about 1.7 billion of new information will be developed per second for all the human inhabitants on this planet. As data is growing at a faster pace, new terms associated with processing and handling data are coming up. These include data science, data mining and machine learning. In the following section- we will give you a detailed insight on these terms.

What is data science?

Data Science deals with both structured and unstructured data. It is a field that includes everything that is associated with the cleansing, preparation and final analysis of data. Data science combines the programming, logical reasoning, mathematics and statistics. It captures data in the most ingenious ways and encourages the ability of looking at things with a different perspective. Likewise, it also cleanses, prepares and aligns the data. To put it more simply, data science is an umbrella of several techniques that are used for extracting the information and the insights of data. Data scientists are responsible for creating the data products and several other data based applications that deal with data in such a way that conventional systems are unable to do.

What is data mining?

Data mining is simply the process of garnering information from huge databases that was previously incomprehensible and unknown and then using that information to make relevant business decisions. To put it more simply, data mining is a set of various methods that are used in the process of knowledge discovery for distinguishing the relationships and patterns that were previously unknown. We can therefore term data mining as a confluence of various other fields like artificial intelligence, data room virtual base management, pattern recognition, visualization of data, machine learning, statistical studies and so on. The primary goal of the process of data mining is to extract information from various sets of data in an attempt to transform it in proper and understandable structures for eventual use. Data mining is thus a process which is used by data scientists and machine learning enthusiasts to convert large sets of data into something more usable.

What is machine learning?

Machine learning is kind of artificial intelligence that is responsible for providing computers the ability to learn about newer data sets without being programmed via an explicit source. It focuses primarily on the development of several computer programs that can transform if and when exposed to newer sets of data. Machine learning and data mining follow the relatively same process. But of them might not be the same. Machine learning follows the method of data analysis which is responsible for automating the model building in an analytical way. It uses algorithms that iteratively gain knowledge from data and in this process; it lets computers find the apparently hidden insights without any help from an external program. In order to gain the best results from data mining, complex algorithms are paired with the right processes and tools.

What is the difference between these three terms?

As we mentioned earlier, data scientists are responsible for coming up with data centric products and applications that handle data in a way which conventional systems cannot. The process of data science is much more focused on the technical abilities of handling any type of data. Unlike data mining and data machine learning it is responsible for assessing the impact of data in a specific product or organization.

While data science focuses on the science of data, data mining is concerned with the process. It deals with the process of discovering newer patterns in big data sets. It might be apparently similar to machine learning, because it categorizes algorithms. However, unlike machine learning, algorithms are only a part of data mining. In machine learning algorithms are used for gaining knowledge from data sets. However, in data mining algorithms are only combined that too as the part of a process. Unlike machine learning it does not completely focus on algorithms.

Source: Firmex.com

منبع ما:
https://www.datasciencecentral.com/profiles/blogs/difference-of-data-science-machine-learning-and-data-mining

لینک دوره:

https://academy.microsoft.com/en-us/tracks/artificial-intelligence/


توضیحات:
سرفصل ها...
Get Started with AI
Use #Python to Work with Data
Use #Math and #Statistics Techniques
Consider Ethics for #AI
Plan and Conduct a Data Study
Build #Machine_Learning Models
Build #Deep_Learning Models
Build #Reinforcement_Learning Models
Develop Applied AI Solutions
Final Project
Microsoft Professional Program Certificate in Artificial Intelligence

از اکانت ماکروسافت شما به سایت edx متصل شده و کورس ها را رایگان در ادکس میگذرانید. در پایان در سایت ماکروسافت گواهی اتمام دوره را دریافت خواهید کرد.

Tensorflow
معرفی #کورس
برنامه رایگان یادگیری عمیق ماکروسافت شامل 10 کورس
Microsoft Professional Program for Artificial Intelligence track

REQUIRED COURSES: 10
HOURS PER COURSE: 16-32
SKILLS: 8

یک نمایش خوب از دو مفهوم False positive and False negative. :))

🔴🔴🔴 خبر فوری: قطع تعداد زیادی از وب سایتها و سرویسهای ایرانی

تعداد زیادی از وب سایتها و سرویسهای ایرانی از ساعتی پیش دچار اختلال شده اند.
برخی از سایتهایی که از دسترس خارج شده اند به شرح زیر هستند:
https://www.certcc.ir/ مرکز ماهر
https://cafebazaar.ir/
http://live.irib.ir/
http://www.nic.ir/
https://divar.ir/
http://yjc.ir/
http://dana.ir/
...

🔴 براساس برخی شواهد، وب سایتهای Host شده روی افرانت، رسپینا، شاتل، آسیاتک، ارتباط زیر ساخت، پارس آنلاین، صبا نت و ... دچار اختلال شده و باز نمی شوند.
همچنین برخی شنیده ها حاکی از این است که تعدادی از سوئیچهای Cisco بدلیل عدم رفع آسیب پذیری بحرانی زیر با حمله روبرو شده و Reset Factory شده اند.
https://tools.cisco.com/security/center/content/CiscoSecurityAdvisory/cisco-sa-20180328-smi2

🔴 مشکل بروز کرده بدلیل آسیب پذیری های سوئیچهای Cisco فقط مربوط به ایران نبوده و هزاران سوئیچ در ده ها کشور را تحت تاثیر خود قرار داده است:
http://www.eweek.com/security/hackers-use-flaw-in-cisco-switches-to-attack-critical-infrastructure
فورا آسیب پذیری فوق را روی سوئیچهای خود Patch کنید!

منبع: کانال دکتر شهرام جمالی

دکترخانلی هئیت علمی دانشگاه تبریز و مدیر گروه مهندسی کامپیوتر دانشکده برق و کامپیوتر پیشنهاد زیر را برای علاقه مندان کامپیوتر دارند:

دوستان لطفا دو كارگاه زیر رو براي كساني كه دنبال كار هستند ارسال كنيد، خودتون هم پيشنهاد مي كنم حتما شركت كنيد.

دکتر خانلی

جزییات کارگاه ها در ادامه این کانال 👇👇👇👇

دوره کوتاه مدت توسعه نرم‌افزار
جزئیات در تصویر

کارگاه توسعه نرم‌افزار
جزییات در تصویر