Intel Introduces new Security Technologies for 3rd Generation Intel Xeon Scalable Platform, Code-named "Ice Lake"

[AleksandarK]

Intel today unveiled the suite of new security features for the upcoming 3rd generation Intel Xeon Scalable platform, code-named "Ice Lake." Intel is doubling down on its Security First Pledge, bringing its pioneering and proven Intel Software Guard Extension (Intel SGX) to the full spectrum of Ice Lake platforms, along with new features that include Intel Total Memory Encryption (Intel TME), Intel Platform Firmware Resilience (Intel PFR) and new cryptographic accelerators to strengthen the platform and improve the overall confidentiality and integrity of data.

Data is a critical asset both in terms of the business value it may yield and the personal information that must be protected, so cybersecurity is a top concern. The security features in Ice Lake enable Intel's customers to develop solutions that help improve their security posture and reduce risks related to privacy and compliance, such as regulated data in financial services and healthcare.



"Protecting data is essential to extracting value from it, and with the capabilities in the upcoming 3rd Gen Xeon Scalable platform, we will help our customers solve their toughest data challenges while improving data confidentiality and integrity. This extends our long history of partnering across the ecosystem to drive security innovations," said Lisa Spelman, Intel corporate vice president in the Data Platform Group and general manager of the Xeon and Memory Group.

Data Protection across the Compute Stack
Technologies such as disk- and network-traffic encryption protect data in storage and during transmission, but data can be vulnerable to interception and tampering while in use in memory. "Confidential computing" is a rapidly emerging usage category that protects data while it is in use in a Trusted Execution Environment (TEE). Intel SGX is the most researched, updated and battle-tested TEE for data center confidential computing, with the smallest attack surface within the system. It enables application isolation in private memory regions, called enclaves, to help protect up to 1 terabyte of code and data while in use.

"Microsoft Azure was the first major public cloud to offer confidential computing, and customers from industries including finance, healthcare, government are using confidential computing on Azure today," said Mark Russinovich, chief technology officer, Microsoft Azure. "Azure has confidential computing options for virtual machines, containers, machine learning, and more. We believe the next-generation Intel Xeon processors with Intel SGX featuring full memory encryption and cryptographic acceleration will help our customers unlock even more confidential computing scenarios."

Customers like the University of California San Francisco (UCSF), NEC, Magnit and other organizations in highly regulated industries have relied on Intel to support their security strategy and leveraged Intel SGX with proven results. For example, healthcare organizations can more securely protect data—including electronic health records—with a trusted computing environment that better preserves patient privacy. In other industries, such as retail, companies rely on Intel to help keep data confidential and protect intellectual property. Intel SGX helps customers unlock new multiparty shared compute scenarios that have been difficult to build in the past due to privacy, security and regulatory requirements.

Intel is also introducing new security capabilities to improve data protection and strengthen the platform, including:

• Full memory encryption: To better protect the entire memory of a platform, Ice Lake introduces a new feature called Intel Total Memory Encryption (Intel TME). Intel TME helps ensure that all memory accessed from the Intel CPU is encrypted, including customer credentials, encryption keys and other IP or personal information on the external memory bus. Intel developed this feature to provide greater protection for system memory against hardware attacks, such as removing and reading the dual in-line memory module (DIMM) after spraying it with liquid nitrogen or installing purpose-built attack hardware. Using the National Institute of Standards and Technology (NIST) storage encryption standard AES XTS, an encryption key is generated using a hardened random number generator in the processor without exposure to software. This allows existing software to run unmodified while better protecting memory.
• Cryptographic acceleration: One of Intel's design goals is to remove or reduce the performance impact of increased security so customers don't have to choose between better protection and acceptable performance. Ice Lake introduces several new instructions used throughout the industry, coupled with algorithmic and software innovations, to deliver breakthrough cryptographic performance. There are two fundamental innovations. The first is a technique to stitch together the operations of two algorithms that typically run in combination yet sequentially, allowing them to execute simultaneously. The second is a method to process multiple independent data buffers in parallel.
• Growing resilience: Sophisticated adversaries may attempt to compromise or disable the platform's firmware to intercept data or take down the server. Ice Lake introduces Intel Platform Firmware Resilience (Intel PFR) to the Intel Xeon Scalable platform to help protect against platform firmware attacks, designed to detect and correct them before they can compromise or disable the machine. Intel PFR uses an Intel FPGA as a platform root of trust to validate critical-to-boot platform firmware components before any firmware code is executed. The firmware components protected can include BIOS Flash, BMC Flash, SPI Descriptor, Intel Management Engine and power supply firmware.

Privacy-preserving, trusted platforms in the upcoming 3rd generation Xeon Scalable processors will help drive even greater innovative services, usage models and solutions for organizations looking to activate the full value of their data.

To learn more about how Intel SGX can help protect sensitive workloads and data, visit www.intel.com/sgx and www.confidentialcomputing.io.

View at TechPowerUp Main Site

 

[Steevo]

Intel is using a FPGA, field programmable gate array.... That can be reprogrammed... For security.....


Sounds about right. Right stupid.

 

[Easo]

Intel is using a FPGA, field programmable gate array.... That can be reprogrammed... For security.....
Sounds about right. Right stupid.

Ok fine, they make it read-only and then find out there was a bug. What then?

 

[ThrashZone]

HI,
They sure have an azure fetish it seems.

 

[Steevo]

Ok fine, they make it read-only and then find out there was a bug. What then?

Have higher testing standard for a multi-Billion dollar company that claims to be an expert in their field. Its like asking what if we make a car that crashes or bursts into flames.

Don't buy their product.

Fix it before you sell it.

its what validation testing is for, Alpha testing, beta testing, etc.... I get paid to do some engineering in my field, and if we don/can't successfully get at least a certain number of units to a standard its back to the drawing board.

 

[Patriot]

SGX is what they removed from 10th gen desktop because it was insecure and unpatchable in 9th gen....
I guess they have figured out how to work around that for icelake?

 

[TheoneandonlyMrK]

And protect power supply firmware?, I'm learning stuff today eh, wtaf well I never, why just why does anyone leave a PSU networked for bios flashing besides the actual maker?.

 

[PowerPC]

Have higher testing standard for a multi-Billion dollar company that claims to be an expert in their field. Its like asking what if we make a car that crashes or bursts into flames.

Don't buy their product.

Fix it before you sell it.

its what validation testing is for, Alpha testing, beta testing, etc.... I get paid to do some engineering in my field, and if we don/can't successfully get at least a certain number of units to a standard its back to the drawing board.

I strongly agree with this. I have worked as a QA Engineer for one of the biggest banks in Europe for two years. The QA procedure, even for something as important as your finances, was literally to do the least amount of testing as possible before you have to move on to the next project. I was advised by the most senior QA engineer there to work like this. It wasn't about actual test coverage, it was just about making the least amount of tests to meet the basic requirement of having tests at all. So you can probably imagine how many holes those tests had.

 

[Easo]

Have higher testing standard for a multi-Billion dollar company that claims to be an expert in their field. Its like asking what if we make a car that crashes or bursts into flames.

You cannot test for every scenario among tens of millions of computers and servers using each new generation regardless. Does not matter how big your budget is or how good QA team you have. It literally is not possible, no matter the vendor, unless we get some kind of AI learning driven testing someday in the future.
Bugs will be found sooner or later, what matters is the response to them.

 

[Steevo]

You cannot test for every scenario among tens of millions of computers and servers using each new generation regardless. Does not matter how big your budget is or how good QA team you have. It literally is not possible, no matter the vendor, unless we get some kind of AI learning driven testing someday in the future.
Bugs will be found sooner or later, what matters is the response to them.

It's all bytes, it's a combination of 1s and 0s, off and on.

I assure you, you can run enough testing to ensure a hard coded product does exactly what it's sold to do.

Making it programmable is where malicious code can enter, and makes it more vulnerable to issues.

Also, stepping is the word for how they fix issues in products.

 

[TheoneandonlyMrK]

It's all bytes, it's a combination of 1s and 0s, off and on.

I assure you, you can run enough testing to ensure a hard coded product does exactly what it's sold to do.

Making it programmable is where malicious code can enter, and makes it more vulnerable to issues.

Also, stepping is the word for how they fix issues in products.

AFAIK every single processor ever released had an errata list, and if it's your opinion that Intel should have known about some of the methods of attack I don't think your thinking it through(rowhamer etc)
A chip for general purpose processing is not the same as a car, or anywhere near as simple a system to mitigate failure on.

 

[AleksandarK]

It's all bytes, it's a combination of 1s and 0s, off and on.

I assure you, you can run enough testing to ensure a hard coded product does exactly what it's sold to do.

Making it programmable is where malicious code can enter, and makes it more vulnerable to issues.

Also, stepping is the word for how they fix issues in products.

Yeah you can run every single scenario in design verification process, but often it is a question of time and how long do you have to test it out. To get a coverage of each scenario of x86 core you need millions of cases and verification for that is insanely huge. Things like SGX are also rather complex, and maybe there is no time to test out each scenario. Thats how vulnerabilities happen. Yes you can, but often you do not test everything. Time is the biggest limit here.

 

[Camm]

Even with this, Intel's still significantly behind AMD's Platform Security features.

Still, its nice to see Intel trying to make up ground, even if I can't see myself rolling out Intel except in legacy support scenarios in the next two to three years.

 

[Steevo]

AFAIK every single processor ever released had an errata list, and if it's your opinion that Intel should have known about some of the methods of attack I don't think your thinking it through(rowhamer etc)
A chip for general purpose processing is not the same as a car, or anywhere near as simple a system to mitigate failure on.

Errata for a piece of hardware with billions of transistors is common.

Errata with a piece of silicon with millions of transistors is unacceptable.

My point isnt that there can't be issues, but making it programmable makes it more, not less vulnerable. As hardware can be implemented to recover (even if it's a BSOD) from unauthorized access.

All it takes is the keys or access to the program and to deconstruct it to gain complete access.

See Jeep and their open programmable CAN bus on vehicles, allowing remote control of a whole vehicle essentially.

 

[Camm]

My point isnt that there can't be issues, but making it programmable makes it more, not less vulnerable. As hardware can be implemented to recover (even if it's a BSOD) from unauthorized access.

Easier to update versus permanent vulnerability, whilst I think you have an excellent point and in a perfect world, I think its better to be completely immutable, I think the reality is vulnerabilities will exist, and I'll be much more comfortable being able to patch up than mitigate.

 

[Caring1]

It's nice to put a face to the next person Intel will throw under a bus when things go pear shaped.

 

[R-T-B]

And protect power supply firmware?, I'm learning stuff today eh, wtaf well I never, why just why does anyone leave a PSU networked for bios flashing besides the actual maker?.

This is for high end servers. Most consumer machines don't even HAVE power supply firmware.

SGX is what they removed from 10th gen desktop because it was insecure and unpatchable in 9th gen....
I guess they have figured out how to work around that for icelake?

SGX is more hardware security bullshit. It's doomed to fail. This is a fail philosophy, from AMD or Intel it's the same garbage.

 

[zlobby]

Proven SGX! Nuff said!