Dark Reading is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them.Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

Vulnerabilities / Threats

11/17/2010
03:54 PM
Connect Directly
Google+
Twitter
RSS
E-Mail
50%
50%

Possible New Threat: Malware That Targets Hardware

Researchers demonstrate proof-of-concept for developing malware that attacks specific hardware processors with 'surgical' precision

French researchers say it's possible to write malware that attacks specific hardware processors rather than operating systems or applications.

Anthony Desnos, Robert Erra, and Eric Filiol, of Ecole Suprieure d'Informatique Electronique Automatique (ESIEA) in Paris, have developed a proof-of-concept for hardware-specific malware, which they consider a step up from Stuxnet and a potentially key weapon in cyberwarfare. The malware can easily identify and target specific hardware systems based on the on-board processor chip, the researchers say.

They used the so-called floating point arithmetic (FPA) to help identify processors, including AMD, Intel Dual-Core and Atom, SPARC, Digital Alpha, Cell, and Atom. Hardware malware doesn't exploit vulnerabilities in hardware -- it preys on actual features: "We just exploit differences in processor features. There will be always such differences," Filiol says.

In order to pinpoint the type of processor, the malware would see how a processor handles certain mathematical calculations. This breed of malware is not any more difficult to create than malware that targets software vulnerabilities, Filiol says. "The malware algorithm is the same. You just have to know which processor-specific information to use to trigger the attack," he says. The tricky part is that information is often a closely held secret, he says.

The researchers maintain that targeted attacks like Stuxnet are a major threat, but it's not always so simple for the attacker to be sure what software is running on a targeted machine. "While it can be very difficult to forecast and envisage which kind of applications is likely to be present on the target system (it can be a secret information), the variety in terms of hardware -- and especially as far as processors are concerned -- is far more reduced due to the very limited number of hardware manufacturers," the researchers wrote in their paper on the malware research.

Hardware malware gives cyberwarfare another weapon. "You can arrange things in such a way that effectively Iran buys a set of computers with Intel processor of a given type and family. Then you can strike them selectively -- and only these computers -- whatever Iran has installed on those computers, [whether it's] Linux, Windows, or any application," Filiol says.

Marc Maiffret, chief technology officer at eEye Digital Security, says he doesn't see hardware malware posing a major threat anytime soon. "While it is interesting to perform this sort of processor fingerprinting, malware will still need to look at other factors to make sure it is hitting the right target, as there is plenty of overlap in systems and what processors they use," Maiffret says. "To put it another way, I think we will continue to see targeting happening more in the way that Stuxnet did it than via processor fingerprinting."

Filiol, meanwhile, says he and his colleagues decided to publish part of their research to raise awareness about this threat. "Even rogue countries and bad guys are doing research. So attacks using those techniques can strike our own countries. That is why we have decided to publish part of our research: to make people aware of the threat," he says.

The malware could be used to wage Distributed Denial-of-Service (DDoS) and any other attack software malware can execute. The idea is for "far more precise and targeted attacks, at a finer level (surgical strikes) in a large network of heterogeneous machines but with generic malware," the research paper says.

There's no way for a processor manufacturer to mitigate such a targeted attack by "patching," either, "unless manufacturers would accept to use the same computation techniques and the same processor designs," he says. But that's obviously not a realistic option, he says.

A full copy of the research is available here (PDF) for download.

Have a comment on this story? Please click "Discuss" below. If you'd like to contact Dark Reading's editors directly, send us a message.

Kelly Jackson Higgins is the Executive Editor of Dark Reading. She is an award-winning veteran technology and business journalist with more than two decades of experience in reporting and editing for various publications, including Network Computing, Secure Enterprise ... View Full Bio

Comment  | 
Print  | 
More Insights
Comments
Oldest First  |  Newest First  |  Threaded View
COVID-19: Latest Security News & Commentary
Dark Reading Staff 9/25/2020
Hacking Yourself: Marie Moe and Pacemaker Security
Gary McGraw Ph.D., Co-founder Berryville Institute of Machine Learning,  9/21/2020
Startup Aims to Map and Track All the IT and Security Things
Kelly Jackson Higgins, Executive Editor at Dark Reading,  9/22/2020
Register for Dark Reading Newsletters
White Papers
Video
Cartoon
Current Issue
Special Report: Computing's New Normal
This special report examines how IT security organizations have adapted to the "new normal" of computing and what the long-term effects will be. Read it and get a unique set of perspectives on issues ranging from new threats & vulnerabilities as a result of remote working to how enterprise security strategy will be affected long term.
Flash Poll
How IT Security Organizations are Attacking the Cybersecurity Problem
How IT Security Organizations are Attacking the Cybersecurity Problem
The COVID-19 pandemic turned the world -- and enterprise computing -- on end. Here's a look at how cybersecurity teams are retrenching their defense strategies, rebuilding their teams, and selecting new technologies to stop the oncoming rise of online attacks.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2020-15208
PUBLISHED: 2020-09-25
In tensorflow-lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, when determining the common dimension size of two tensors, TFLite uses a `DCHECK` which is no-op outside of debug compilation modes. Since the function always returns the dimension of the first tensor, malicious attackers can ...
CVE-2020-15209
PUBLISHED: 2020-09-25
In tensorflow-lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, a crafted TFLite model can force a node to have as input a tensor backed by a `nullptr` buffer. This can be achieved by changing a buffer index in the flatbuffer serialization to convert a read-only tensor to a read-write one....
CVE-2020-15210
PUBLISHED: 2020-09-25
In tensorflow-lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, if a TFLite saved model uses the same tensor as both input and output of an operator, then, depending on the operator, we can observe a segmentation fault or just memory corruption. We have patched the issue in d58c96946b and ...
CVE-2020-15211
PUBLISHED: 2020-09-25
In TensorFlow Lite before versions 1.15.4, 2.0.3, 2.1.2, 2.2.1 and 2.3.1, saved models in the flatbuffer format use a double indexing scheme: a model has a set of subgraphs, each subgraph has a set of operators and each operator has a set of input/output tensors. The flatbuffer format uses indices f...
CVE-2020-15212
PUBLISHED: 2020-09-25
In TensorFlow Lite before versions 2.2.1 and 2.3.1, models using segment sum can trigger writes outside of bounds of heap allocated buffers by inserting negative elements in the segment ids tensor. Users having access to `segment_ids_data` can alter `output_index` and then write to outside of `outpu...