Security — The Dark Side of the Cloud

By Steve Campbell

January 25, 2010

Cloud computing is a new computing paradigm for many but for the rest of us it is simply today’s version of timesharing – Timesharing 2.0. On-demand or pay-for-usage has been the norm for many HPC organizations for several decades. These users either never had the budget for their own computing resources or the project only needed limited access to powerful compute resources.

In that sense, HPC users, like the biggest commercial users, already trust cloud computing with their proprietary applications, data and results. They have been using pay-for-usage services for years and many have evolved from the early days of timesharing. In many cases, supercomputing centers and government research labs provide the compute resources. If you are a commercial HPC user in oil & gas, financial services, manufacturing or other industry, the compute resources will probably be found in the corporate datacenter.

This HPC user community has pioneered the necessary tools to allocate, measure and control access to specific users and projects while protecting the users from unauthorized access or modification of applications and data or malicious erasure or premature disclosure of results. This community also developed sophisticated accounting and charge back software that kept track of everything from CPU cycles to memory usage to access time and storage used. Suffice it to say that HPC users are well ahead of their counterparts in the commercial datacenter, and the latter would do well to look toward the former for some guidance in this area.

Without a doubt, the biggest challenge to cloud computing is security – the dark side of the cloud. In the cloud paradigm, the user community does not or should not care about the physical side of business operations. In most cases, the physical infrastructure is housed, managed and owned by a third party, and you pay for resources used just like the electric and gas utilities. Despite all these wonderful capabilities and features, security remains as much of a concern for the HPC community as it does for the consumers concerned about protecting their identity and credit card information.

Imagine for a moment the business ramifications if the results of critical drug data or aircraft design were changed and compromised by malicious activity or they were released to the world prematurely. The real and intangible costs to your company can be devastating.

Threats to the network and information security have been occurring for decades, nothing new. However, the complexity and scale of attacks are rising at an alarming rate, presenting organizations with a huge challenge as they struggle to defend against this ever-present threat. Today, cybercrime is more lucrative and less risky than other forms of criminal activity. Threat levels and attacks are on the rise, striking more and more businesses. Estimates for disruption, data theft and other nefarious activities were pegged at a staggering $1 trillion for 2008. Certainly more than a round-off error!

Just this month, the news headlines in CNET News include “Google China insiders may have helped with attack” and in the Wall Street Journal: “Fallout From Cyber Attack Spreads.” CCTV.com reported, “China’s largest search engine paralyzed in cyber-attack….” And a ZDNet headline on Jan. 21 read: “Microsoft knew of IE zero-day flaw since last September.”

In July 2009, the associatedcontent.com headlines read “Near-Simultaneous Cyber Attacks Down U.S. Government Websites.” The article reported that the attack targeted the “White House, Pentagon, NYSE, Secret Service, NSA, Homeland Security, State, Nasdaq, Treasury, FAA, FTC, and DOT Websites.”

The low risk and low-cost of entry of cyber-crime make it an attractive and lucrative “business.” Cloud-based computing exacerbates the situation by facilitating access to increasing amounts of information. IT organizations have a hard enough time defending their in-house private cloud resources. Companies offering public cloud, pay-for-usage models are faced with a more difficult challenge since they must serve multiple organizations on the same platform. At the same time, there is an opportunity for innovation of flexible cloud-based security service offerings.

The criminal element employs powerful tools such as botnets, enabling attackers to infiltrate large numbers of machines. The “2009 Emerging Cyber Threats Report from Georgia Tech Information Security Center (GTISC)” estimates that botnet-affected machines may comprise 15 percent of online computers. Another report compiled by Panda Labs estimates that in the second quarter of 2008 10 million botnet computers were used to distribute spam and malware across the Internet each day. With the growth of the cloud paradigm, more and more mission critical information will flow over the Web to publicly-hosted cloud services. The conventional wisdom of defending the perimeter is insufficient for this dynamic distributed environment. One element in common across commercial enterprise applications is that users must consider security before signing up for public cloud services.

During SC09, I met with many of the HPC infrastructure vendors and also spoke with some real-world HPC cloud users about the concerns they have using cloud computing for their workloads. (This was not a structured industry survey.) Some did express concerns about security but mainly in the context of using public cloud resources versus their private cloud resources. However, they also expressed concerns about transitioning their HPC workloads from in-house resources to external public cloud resources, as it is a very different scenario and from commercial workloads. From a security standpoint the concerns ranged from unauthorized access to exposure of critical information to malicious activity. Additional concerns include the movement and encryption of data to public clouds and the subsequent persistence once workloads have been completed. Has the data really been deleted? It is all about the data integrity.

HPC users often have many options available for running their workloads. For example, an academic user may have access to in-house central computing resources shared between multiple departments, or even access to large-scale supercomputing centers. In this environment the user data, results and applications are still very much ‘in-house’ and even though there is some security risk, the users are better protected in this environment. HPC users in private industry, especially those in large-scale multinational companies, may have the option of private clouds available for their workloads, and like HPC academic users, have fewer security concerns. However, if the HPC user is looking at commercial third-party cloud providers of public clouds, whether it is Amazon’s EC2, Google’s App Engine or better still, HPC-specific cloud vendors, they should spend the time to ensure that these vendors fully address their security issues, encryption, and persistence.

To those organizations that do not have internal private clouds and want to use cloud computing from a third party vendor, I recommend you consider the following five security evaluation criteria:

  1. Evaluate the vendor’s security features very carefully. Ensure that they provide more than just password-protected access.
     
  2. Look into the collaboration tools and resource sharing to prevent data leakage. Security is all about the data.
     
  3. Look into authentication and the basic infrastructure security. What happens in the event of a disaster? What’s their disaster recovery plan, backup procedures and how often do they test this process? Has the provider ever had a failure or security breach and if so what happened?
     
  4. Can they build a private cloud for your workload? What’s their data persistence policy? Can they guarantee data transfer security form in-house resources to public cloud?
     
  5. Ask to review their best practices policy and procedures and check to see if it includes security audits and regular testing.

Cloud computing is not so much a new technology as it is a new delivery model, but its impact will be enormous. Research firm IDC estimated that worldwide cloud services in 2009 were $17.4 billion, and are forecasted to grow to $44.2 billion in 2013. The economies of scale and centralized resources create new security challenges to an already stressed IT infrastructure.

This concentration of resources and data will be a tempting target for cyber criminals. Consequently, cloud-based security must be more robust. Spend the time to evaluate the security and make sure it is designed in and not added on after a breach. Partner with a trusted vendor. And if in doubt, seek advice.

About the Author

Steve Campbell, an HPC Industry Consultant and HPC/Cloud Evangelist, has held senior VP positions in product management and product marketing for HPC and Enterprise vendors. Campbell has served in the vice president of marketing capacity for Hitachi, Sun Microsystems, FPS Computing and has also had lead marketing roles in Convex Computer Corporation and Scientific Computer Systems. Campbell has also served on the boards of and as interim CEO/CMO of several early-stage technology companies.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire