recentpopularlog in


« earlier   
Attacking Private Networks from the Internet with DNS Rebinding
The home WiFi network is a sacred place; your own local neighborhood of cyberspace. There we connect our phones, laptops, and “smart” devices to each other and to the Internet and in turn we improve…
dns  exploit  hack  hacking  network 
2 days ago by nharbour
The crooked timber of humanity | 1843
"The world’s first national data network was constructed in France during the 1790s. It was a mechanical telegraph system, consisting of chains of towers, each of which had a system of movable wooden arms on top."
history  crime  security  hacking  dopost  networks 
3 days ago by niksilver
Community driven knowledge dedicated to learning hardware.
electronics  hacking  hardware  raspberrypi  arduino  tutorials  artciles  videos 
3 days ago by jonlabelle
How to stealthily poison neural network chips in the supply chain • The Register
Thomas Claburn:
<p>"Hardware Trojans can be inserted into a device during manufacturing by an untrusted semiconductor foundry or through the integration of an untrusted third-party IP," [Clemson University researchers Joseph Clements and Yingjie Lao] <a href="">explain in their pape</a>r. "Furthermore, a foundry or even a designer may possibly be pressured by the government to maliciously manipulate the design for overseas products, which can then be weaponized."

The purpose of such deception, the researchers explain, would be to introduce hidden functionality – a Trojan – in chip circuitry. The malicious code would direct a neural network to classify a selected input trigger in a specific way while remaining undetectable in test data.

"For example, an adversary in a position to profit from excessive or improper sale of specific pharmaceutics could inject hardware Trojans on a device for diagnosing patients using neural network models," they suggest. "The attacker could cause the device to misdiagnose selected patients to gain additional profit."

They claim they were able to prototype their scheme by altering only 0.03% of the neurons in one layer of a seven-layer convolutional neural network.

Clements and Lao say they believe adversarial training combined with hardware Trojan detection represent a promising approach to defending against their threat scenario. The adversarial training would increase the number of network network neurons that would have to be altered to inject malicious behavior, thereby making the Trojan large enough potentially to detect.</p>
ai  neuralnetwork  hacking 
3 days ago by charlesarthur

Copy this bookmark:

to read