Websites Have a New Way To Spy On Visitors: Analyzing Their SSD Activity (arstechnica.com)
(Wednesday May 27, 2026 @11:30PM (BeauHD)
from the PSA dept.)
- Reference: 0183431634
- News link: https://hardware.slashdot.org/story/26/05/27/2153246/websites-have-a-new-way-to-spy-on-visitors-analyzing-their-ssd-activity
- Source link: https://arstechnica.com/security/2026/05/websites-have-a-new-way-to-spy-on-visitors-analyzing-their-ssd-activity/
An anonymous reader quotes a report from Ars Technica:
> Now sites have a new way to spy on their visitors: [1]measuring subtle interactions with their solid-state drives . The technique, named FROST (fingerprinting remotely using OPFS-based SSD timing), allows sites to monitor other sites a visitor is viewing and what apps are open on their devices. The technique, laid out in a [2]research paper (PDF), exploits a [3]side channel , a form of leak resulting from physical manifestations such as electromagnetic emanations, data caches, or the time required to complete a task. By measuring the manifestations, attackers can decrypt encrypted traffic and infer other confidential data.
>
> The attack that FROST uses is known as a contention side channel, which measures the interaction of various processes all using (or competing for) a given resource. By measuring the timing of certain I/O (input-output) operations of the SSD a visitor is using, the researchers were able to determine the websites open in other tabs -- even on other browsers -- and the apps that were open on the visitor's device. FROST requires no interaction from the visitor other than opening the site hosting the attack. [...] Unlike previous contention side-channel attacks on SSDs, FROST runs exclusively in the browser. It uses JavaScript that interacts with the [4]OPFS (origin private file system), an allocated storage space that's reserved for a specific site to run code needed to complete a given task. Websites can create one with no interaction required by the visitor.
>
> While each file system is sandboxed, meaning it's isolated from other websites and from the device system itself, the JavaScript can measure the I/O interactions. Then, by running those interactions through a pretrained [5]convolutional neural network -- a system that uses deep learning to analyze text, audio, and images -- the attacker can deduce various apps and websites open on the device. "The attacker continuously measures SSD contention by performing random reads from a large OPFS file," the researchers explained. "SSD contention caused by user activity causes measurable latency differences for these read operations. By training a convolutional neural network (CNN) on these traces, the attacker can fingerprint user activity on the host system by classifying new traces using the trained model."
[1] https://arstechnica.com/security/2026/05/websites-have-a-new-way-to-spy-on-visitors-analyzing-their-ssd-activity/
[2] https://hannesweissteiner.com/pdfs/frost.pdf
[3] https://en.wikipedia.org/wiki/Side-channel_attack
[4] https://developer.mozilla.org/en-US/docs/Web/API/File_System_API/Origin_private_file_system
[5] https://en.wikipedia.org/wiki/Convolutional_neural_network
> Now sites have a new way to spy on their visitors: [1]measuring subtle interactions with their solid-state drives . The technique, named FROST (fingerprinting remotely using OPFS-based SSD timing), allows sites to monitor other sites a visitor is viewing and what apps are open on their devices. The technique, laid out in a [2]research paper (PDF), exploits a [3]side channel , a form of leak resulting from physical manifestations such as electromagnetic emanations, data caches, or the time required to complete a task. By measuring the manifestations, attackers can decrypt encrypted traffic and infer other confidential data.
>
> The attack that FROST uses is known as a contention side channel, which measures the interaction of various processes all using (or competing for) a given resource. By measuring the timing of certain I/O (input-output) operations of the SSD a visitor is using, the researchers were able to determine the websites open in other tabs -- even on other browsers -- and the apps that were open on the visitor's device. FROST requires no interaction from the visitor other than opening the site hosting the attack. [...] Unlike previous contention side-channel attacks on SSDs, FROST runs exclusively in the browser. It uses JavaScript that interacts with the [4]OPFS (origin private file system), an allocated storage space that's reserved for a specific site to run code needed to complete a given task. Websites can create one with no interaction required by the visitor.
>
> While each file system is sandboxed, meaning it's isolated from other websites and from the device system itself, the JavaScript can measure the I/O interactions. Then, by running those interactions through a pretrained [5]convolutional neural network -- a system that uses deep learning to analyze text, audio, and images -- the attacker can deduce various apps and websites open on the device. "The attacker continuously measures SSD contention by performing random reads from a large OPFS file," the researchers explained. "SSD contention caused by user activity causes measurable latency differences for these read operations. By training a convolutional neural network (CNN) on these traces, the attacker can fingerprint user activity on the host system by classifying new traces using the trained model."
[1] https://arstechnica.com/security/2026/05/websites-have-a-new-way-to-spy-on-visitors-analyzing-their-ssd-activity/
[2] https://hannesweissteiner.com/pdfs/frost.pdf
[3] https://en.wikipedia.org/wiki/Side-channel_attack
[4] https://developer.mozilla.org/en-US/docs/Web/API/File_System_API/Origin_private_file_system
[5] https://en.wikipedia.org/wiki/Convolutional_neural_network
Welp! (Score:2)
by jenningsthecat ( 1525947 )
SSDs have gotten stoopid expensive anyway, so maybe it's a good time to go back to spinning rust.
Then again, might this attack even work on the the silicon of a magnetic drive? Or is the buffer too small to be vulnerable in the same way?
Trivial to obfuscate (Score:1)
by RightwingNutjob ( 1302813 )
So this side channel signal can be obfuscated with randomly timed broad frequency reads and writes to the filesystem, presumably? Since the signal it is looking for is latency caused by patterns of reads and writes that fingerprint an application?
adblock and privacy badger (Score:3)
Clearly an exploit, the sites that use this should be blacklisted, I dont care if its a large site or not. Using a hack is illegal and should be treated as such.
Re: (Score:1)
I'd rather whitelist the few sites that actually need OPFS (along with other direct filesystem access APIs).
Too bad browser vendors are terrified of presenting users with a proper permissions interface... God forbid they ask people to think.
Instead what we're probably gonna get is timing fuzzing, adding a huge amount of code to the browser to slow down file access.
Re: (Score:2)
I'm stunned this even exists [1]https://developer.mozilla.org/... [mozilla.org]
[1] https://developer.mozilla.org/en-US/docs/Web/API/File_System_API/Origin_private_file_system