GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → asm → deep_spectre

asm / deep_spectre

Licence: other
Deep learning side channel privileged memory reader

Programming Languages

c
50402 projects - #5 most used programming language
python
139335 projects - #7 most used programming language

Labels

deep-learningtensorflowkerasspectre

Projects that are alternatives of or similar to deep spectre

Spectre Attack
Example of using revealed "Spectre" exploit (CVE-2017-5753 and CVE-2017-5715)
Stars: ✭ 690 (+1400%)
Mutual labels:  spectre
Spectre
GPU-accelerated Factors analysis library and Backtester
Stars: ✭ 157 (+241.3%)
Mutual labels:  spectre
spectre-canjs
A data administration component library built on the Spectre.css framework enabled with CanJS
Stars: ✭ 25 (-45.65%)
Mutual labels:  spectre
In Spectre Meltdown
This tool allows to check speculative execution side-channel attacks that affect many modern processors and operating systems designs. CVE-2017-5754 (Meltdown) and CVE-2017-5715 (Spectre) allows unprivileged processes to steal secrets from privileged processes. These attacks present 3 different ways of attacking data protection measures on CPUs enabling attackers to read data they shouldn't be able to. This tool is originally based on Microsoft: https://support.microsoft.com/en-us/help/4073119/protect-against-speculative-execution-side-channel-vulnerabilities-in
Stars: ✭ 86 (+86.96%)
Mutual labels:  spectre
Spectre
Spectre.css - A Lightweight, Responsive and Modern CSS Framework
Stars: ✭ 10,938 (+23678.26%)
Mutual labels:  spectre
Spectrepoc
Proof of concept code for the Spectre CPU exploit.
Stars: ✭ 239 (+419.57%)
Mutual labels:  spectre
Hardware And Firmware Security Guidance
Guidance for the Spectre, Meltdown, Speculative Store Bypass, Rogue System Register Read, Lazy FP State Restore, Bounds Check Bypass Store, TLBleed, and L1TF/Foreshadow vulnerabilities as well as general hardware and firmware security guidance. #nsacyber
Stars: ✭ 408 (+786.96%)
Mutual labels:  spectre
kleespectre
KLEESpectre is a symbolic execution engine with speculation semantic and cache modelling
Stars: ✭ 31 (-32.61%)
Mutual labels:  spectre
Ex money
A [work-in-progress] self-hosted personal finance app
Stars: ✭ 154 (+234.78%)
Mutual labels:  spectre
meltdown-spectre-bios-list
a list of BIOS/Firmware fixes adressing CVE-2017-5715, CVE-2017-5753, CVE-2017-5754
Stars: ✭ 16 (-65.22%)
Mutual labels:  spectre
Hexo Theme Spectre
A modern, simple & elegant theme for Hexo
Stars: ✭ 109 (+136.96%)
Mutual labels:  spectre
Spectre Meltdown Poc
A semi-demi-working proof of concept for a mix of spectre and meltdown vulnerabilities
Stars: ✭ 127 (+176.09%)
Mutual labels:  spectre
spectre-attack-demo
Reproducing malicious memory reading on Intel i5 and Intel Xeon using a Spectre attack
Stars: ✭ 87 (+89.13%)
Mutual labels:  spectre
Spectre macos
Tools to run MacOS on HP Spectre x360 (Late-2016 / Early-2017, Kaby Lake)
Stars: ✭ 22 (-52.17%)
Mutual labels:  spectre
gotify-push
Chrome Extension for Send Push Notification 🔔 to gotify/server ☁
Stars: ✭ 32 (-30.43%)
Mutual labels:  spectre
Specucheck
SpecuCheck is a Windows utility for checking the state of the software mitigations and hardware against CVE-2017-5754 (Meltdown), CVE-2017-5715 (Spectre v2), CVE-2018-3260 (Foreshadow), and CVE-2018-3639 (Spectre v4)
Stars: ✭ 542 (+1078.26%)
Mutual labels:  spectre
Spectre Attack Sgx
Spectre attack against SGX enclave
Stars: ✭ 214 (+365.22%)
Mutual labels:  spectre
hardware-attacks-state-of-the-art
Microarchitectural exploitation and other hardware attacks.
Stars: ✭ 29 (-36.96%)
Mutual labels:  spectre
psf utils
Read Spectre PSF files
Stars: ✭ 20 (-56.52%)
Mutual labels:  spectre
alias-wallet
Official Alias source code repository
Stars: ✭ 5 (-89.13%)
Mutual labels:  spectre
View All Similar Projects ➔

Deep Spectre

Deep Spectre is a deep learning side channel privileged memory reader heavily based on the PoC found here. I've written a Medium post explaining the deep learning code and you can read more about Spectre in CVE-2017-5753 and CVE-2017-5715 or check out the whitepaper and Google Project Zero post.

Installing

The Python 3 C API is used to glue the PoC code to the Keras deep learning API. Thus, you'll have to compile and install a native module. Simply run:

python setup.py install

After installing the packages listed in requirements.txt, start the program and you should see the results below

./spectre.py
Using TensorFlow backend.
Collecting training data...
Scaling data between 0-1...
Training deep model...
Train on 48000 samples, validate on 16000 samples
Epoch 1/10
48000/48000 [==============================] - 4s 83us/step - loss: 2.9168 - acc: 0.3363 - val_loss: 0.7985 - val_acc: 0.8276
Epoch 2/10
48000/48000 [==============================] - 4s 73us/step - loss: 0.4543 - acc: 0.9007 - val_loss: 0.3505 - val_acc: 0.9204
Epoch 3/10
48000/48000 [==============================] - 4s 75us/step - loss: 0.2802 - acc: 0.9367 - val_loss: 0.2825 - val_acc: 0.9335
Epoch 4/10
48000/48000 [==============================] - 3s 73us/step - loss: 0.2516 - acc: 0.9441 - val_loss: 0.2948 - val_acc: 0.9293
Epoch 5/10
48000/48000 [==============================] - 4s 73us/step - loss: 0.2368 - acc: 0.9451 - val_loss: 0.2640 - val_acc: 0.9361
Epoch 6/10
48000/48000 [==============================] - 4s 73us/step - loss: 0.2320 - acc: 0.9460 - val_loss: 0.2765 - val_acc: 0.9360
Epoch 7/10
48000/48000 [==============================] - 3s 73us/step - loss: 0.2405 - acc: 0.9458 - val_loss: 0.2588 - val_acc: 0.9376
Epoch 8/10
48000/48000 [==============================] - 4s 74us/step - loss: 0.2324 - acc: 0.9468 - val_loss: 0.2502 - val_acc: 0.9403
Epoch 9/10
48000/48000 [==============================] - 4s 73us/step - loss: 0.2269 - acc: 0.9474 - val_loss: 0.2452 - val_acc: 0.9408
Epoch 10/10
48000/48000 [==============================] - 3s 72us/step - loss: 0.2277 - acc: 0.9467 - val_loss: 0.2663 - val_acc: 0.9392
The secret message is: The Magic Words are Squeamish Ossifrage.

License

MIT

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].