home.social

#spikingneuralnetwork — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #spikingneuralnetwork, aggregated by home.social.

fetched live
  1. Been working on something for a while and finally put it out there, a public security challenge against a threshold cryptography system I built for my own infrastructure.

    Four servers, four countries, four hosting providers. The group signing key was generated distributedly (Pedersen DKG), no single server holds the full secret. I literally can't extract it myself. The challenge is to forge a valid FROST Ed25519 signature against today's published challenge string.

    What makes it different from a typical CTF:

    → It's not a weekend event. It runs 24/7 for 90 days. The servers are real production boxes running real software (Nextcloud, Gitea, a team API, Grafana). Not docker containers with planted vulns.

    → Post-quantum hybrid. The audit chain carries ML-DSA-44 signatures alongside the FROST threshold sigs, with a downgrade-detection flag baked into the signed payload. Stripping the PQ signature invalidates the classical one.

    → There's a spiking neural network watching the cluster. 258 neurons with STDP learning and four neuromodulators (dopamine, noradrenaline, acetylcholine, serotonin). It processes DAG events, network metrics, and system telemetry as spike trains. A local LLM reads the brain's internal state every five minutes and reports what it observes. Currently it says the cluster is calm. I want to see what it says when someone's actually poking around.

    The detection layer is consensus-based. Cross-peer Merkle verification, honey ports, file canaries, DNS sentinels — but quarantine requires multiple observers to agree before acting. One node can't panic the cluster on its own.

    I've already broken it myself twice during deployment. Rolled a binary update and got cascade-quarantined by my own Merkle checker. Tripped a file canary rotating honeypot credentials. Those incidents are published. The system catches real mistakes.

    Five tiers from foothold to crown jewel. No cash bounty, just your name on the board, CVE attribution, and write-up rights. Safe harbour under disclose.io terms.

    hyveguard.com

    #infosec #security #cryptography #thresholdcrypto #ctf #FROST #postquantum #pentest #redteam #hacking #spikingneuralnetwork #neuromorphic

    @eff @mttaggart @GossiTheDog @briankrebs @lcamtuf

  2. Been working on something for a while and finally put it out there, a public security challenge against a threshold cryptography system I built for my own infrastructure.

    Four servers, four countries, four hosting providers. The group signing key was generated distributedly (Pedersen DKG), no single server holds the full secret. I literally can't extract it myself. The challenge is to forge a valid FROST Ed25519 signature against today's published challenge string.

    What makes it different from a typical CTF:

    → It's not a weekend event. It runs 24/7 for 90 days. The servers are real production boxes running real software (Nextcloud, Gitea, a team API, Grafana). Not docker containers with planted vulns.

    → Post-quantum hybrid. The audit chain carries ML-DSA-44 signatures alongside the FROST threshold sigs, with a downgrade-detection flag baked into the signed payload. Stripping the PQ signature invalidates the classical one.

    → There's a spiking neural network watching the cluster. 258 neurons with STDP learning and four neuromodulators (dopamine, noradrenaline, acetylcholine, serotonin). It processes DAG events, network metrics, and system telemetry as spike trains. A local LLM reads the brain's internal state every five minutes and reports what it observes. Currently it says the cluster is calm. I want to see what it says when someone's actually poking around.

    The detection layer is consensus-based. Cross-peer Merkle verification, honey ports, file canaries, DNS sentinels — but quarantine requires multiple observers to agree before acting. One node can't panic the cluster on its own.

    I've already broken it myself twice during deployment. Rolled a binary update and got cascade-quarantined by my own Merkle checker. Tripped a file canary rotating honeypot credentials. Those incidents are published. The system catches real mistakes.

    Five tiers from foothold to crown jewel. No cash bounty, just your name on the board, CVE attribution, and write-up rights. Safe harbour under disclose.io terms.

    hyveguard.com

    #infosec #security #cryptography #thresholdcrypto #ctf #FROST #postquantum #pentest #redteam #hacking #spikingneuralnetwork #neuromorphic

    @eff @mttaggart @GossiTheDog @briankrebs @lcamtuf

  3. Been working on something for a while and finally put it out there, a public security challenge against a threshold cryptography system I built for my own infrastructure.

    Four servers, four countries, four hosting providers. The group signing key was generated distributedly (Pedersen DKG), no single server holds the full secret. I literally can't extract it myself. The challenge is to forge a valid FROST Ed25519 signature against today's published challenge string.

    What makes it different from a typical CTF:

    → It's not a weekend event. It runs 24/7 for 90 days. The servers are real production boxes running real software (Nextcloud, Gitea, a team API, Grafana). Not docker containers with planted vulns.

    → Post-quantum hybrid. The audit chain carries ML-DSA-44 signatures alongside the FROST threshold sigs, with a downgrade-detection flag baked into the signed payload. Stripping the PQ signature invalidates the classical one.

    → There's a spiking neural network watching the cluster. 258 neurons with STDP learning and four neuromodulators (dopamine, noradrenaline, acetylcholine, serotonin). It processes DAG events, network metrics, and system telemetry as spike trains. A local LLM reads the brain's internal state every five minutes and reports what it observes. Currently it says the cluster is calm. I want to see what it says when someone's actually poking around.

    The detection layer is consensus-based. Cross-peer Merkle verification, honey ports, file canaries, DNS sentinels — but quarantine requires multiple observers to agree before acting. One node can't panic the cluster on its own.

    I've already broken it myself twice during deployment. Rolled a binary update and got cascade-quarantined by my own Merkle checker. Tripped a file canary rotating honeypot credentials. Those incidents are published. The system catches real mistakes.

    Five tiers from foothold to crown jewel. No cash bounty, just your name on the board, CVE attribution, and write-up rights. Safe harbour under disclose.io terms.

    hyveguard.com

    #infosec #security #cryptography #thresholdcrypto #ctf #FROST #postquantum #pentest #redteam #hacking #spikingneuralnetwork #neuromorphic

    @eff @mttaggart @GossiTheDog @briankrebs @lcamtuf

  4. New preprint! What happens if you add neuromodulation to spiking neural networks and let them go wild with it? TLDR: it can improve performance especially in challenging sensory processing tasks.

    Preprint:

    biorxiv.org/content/10.1101/20

    Short explainer thread on Bluesky:

    bsky.app/profile/neural-reckon

    #neuroscience #ComputationalNeuroscience #SpikingNeuralNetwork

  5. New preprint! What happens if you add neuromodulation to spiking neural networks and let them go wild with it? TLDR: it can improve performance especially in challenging sensory processing tasks.

    Preprint:

    biorxiv.org/content/10.1101/20

    Short explainer thread on Bluesky:

    bsky.app/profile/neural-reckon

    #neuroscience #ComputationalNeuroscience #SpikingNeuralNetwork

  6. New preprint! What happens if you add neuromodulation to spiking neural networks and let them go wild with it? TLDR: it can improve performance especially in challenging sensory processing tasks.

    Preprint:

    biorxiv.org/content/10.1101/20

    Short explainer thread on Bluesky:

    bsky.app/profile/neural-reckon

    #neuroscience #ComputationalNeuroscience #SpikingNeuralNetwork

  7. New preprint! What happens if you add neuromodulation to spiking neural networks and let them go wild with it? TLDR: it can improve performance especially in challenging sensory processing tasks.

    Preprint:

    biorxiv.org/content/10.1101/20

    Short explainer thread on Bluesky:

    bsky.app/profile/neural-reckon

    #neuroscience #ComputationalNeuroscience #SpikingNeuralNetwork

  8. New preprint! What happens if you add neuromodulation to spiking neural networks and let them go wild with it? TLDR: it can improve performance especially in challenging sensory processing tasks.

    Preprint:

    biorxiv.org/content/10.1101/20

    Short explainer thread on Bluesky:

    bsky.app/profile/neural-reckon

    #neuroscience #ComputationalNeuroscience #SpikingNeuralNetwork

  9. Submissions (short!) due for SNUFA spiking neural networks conference in <2 weeks!

    forms.cloud.microsoft/e/XkZLav

    More info at snufa.net/2025/

    Note that we normally get around 700 participants and recordings go on YouTube and get 100s-1000s views, so it's a good place to promote your work.

    Please repost.

    #neuroscience #SpikingNeuralNetwork #SpikingNeuralNetworks #snn #snufa

  10. Submissions (short!) due for SNUFA spiking neural networks conference in <2 weeks!

    forms.cloud.microsoft/e/XkZLav

    More info at snufa.net/2025/

    Note that we normally get around 700 participants and recordings go on YouTube and get 100s-1000s views, so it's a good place to promote your work.

    Please repost.

    #neuroscience #SpikingNeuralNetwork #SpikingNeuralNetworks #snn #snufa

  11. Submissions (short!) due for SNUFA spiking neural networks conference in <2 weeks!

    forms.cloud.microsoft/e/XkZLav

    More info at snufa.net/2025/

    Note that we normally get around 700 participants and recordings go on YouTube and get 100s-1000s views, so it's a good place to promote your work.

    Please repost.

    #neuroscience #SpikingNeuralNetwork #SpikingNeuralNetworks #snn #snufa

  12. Submissions (short!) due for SNUFA spiking neural networks conference in <2 weeks!

    forms.cloud.microsoft/e/XkZLav

    More info at snufa.net/2025/

    Note that we normally get around 700 participants and recordings go on YouTube and get 100s-1000s views, so it's a good place to promote your work.

    Please repost.

    #neuroscience #SpikingNeuralNetwork #SpikingNeuralNetworks #snn #snufa

  13. Submissions (short!) due for SNUFA spiking neural networks conference in <2 weeks!

    forms.cloud.microsoft/e/XkZLav

    More info at snufa.net/2025/

    Note that we normally get around 700 participants and recordings go on YouTube and get 100s-1000s views, so it's a good place to promote your work.

    Please repost.

    #neuroscience #SpikingNeuralNetwork #SpikingNeuralNetworks #snn #snufa

  14. I recently played around with #RateModels using #NESTsimulator. Compared to #SNN, RM focus on average firing rates of #NeuronPopulations, simplifying analysis of large networks. They effectively capture collective dynamics like #oscillations and #synchronization, though they miss precise spike timing details. Thus, both approaches have their merits. Here is a brief overview:

    🌍 fabriziomusacchio.com/blog/202

    #CompNeuro #Neuroscience #Python #PythonTutorial #SpikingNeuralNetwork

  15. I recently played around with #RateModels using #NESTsimulator. Compared to #SNN, RM focus on average firing rates of #NeuronPopulations, simplifying analysis of large networks. They effectively capture collective dynamics like #oscillations and #synchronization, though they miss precise spike timing details. Thus, both approaches have their merits. Here is a brief overview:

    🌍 fabriziomusacchio.com/blog/202

    #CompNeuro #Neuroscience #Python #PythonTutorial #SpikingNeuralNetwork

  16. I recently played around with #RateModels using #NESTsimulator. Compared to #SNN, RM focus on average firing rates of #NeuronPopulations, simplifying analysis of large networks. They effectively capture collective dynamics like #oscillations and #synchronization, though they miss precise spike timing details. Thus, both approaches have their merits. Here is a brief overview:

    🌍 fabriziomusacchio.com/blog/202

    #CompNeuro #Neuroscience #Python #PythonTutorial #SpikingNeuralNetwork

  17. I recently played around with #RateModels using #NESTsimulator. Compared to #SNN, RM focus on average firing rates of #NeuronPopulations, simplifying analysis of large networks. They effectively capture collective dynamics like #oscillations and #synchronization, though they miss precise spike timing details. Thus, both approaches have their merits. Here is a brief overview:

    🌍 fabriziomusacchio.com/blog/202

    #CompNeuro #Neuroscience #Python #PythonTutorial #SpikingNeuralNetwork

  18. 📚 New preprint by Vafaii, Galor & Yates: Brain-like variational inference. They derive #SpikingNeuralNetwork dynamics directly from variational free energy minimization via online natural #GradientDescent, yielding the iterative Poisson #VAE (iP-VAE) with strong sparsity, reconstruction & #BiologicalPlausibility.

    🌍 arxiv.org/abs/2410.19315
    🧑‍💻 github.com/hadivafaii/Iterativ

    #Neuroscience #MachineLearning #SNN #CompNeuro

  19. 📚 New preprint by Vafaii, Galor & Yates: Brain-like variational inference. They derive #SpikingNeuralNetwork dynamics directly from variational free energy minimization via online natural #GradientDescent, yielding the iterative Poisson #VAE (iP-VAE) with strong sparsity, reconstruction & #BiologicalPlausibility.

    🌍 arxiv.org/abs/2410.19315
    🧑‍💻 github.com/hadivafaii/Iterativ

    #Neuroscience #MachineLearning #SNN #CompNeuro

  20. 📚 New preprint by Vafaii, Galor & Yates: Brain-like variational inference. They derive #SpikingNeuralNetwork dynamics directly from variational free energy minimization via online natural #GradientDescent, yielding the iterative Poisson #VAE (iP-VAE) with strong sparsity, reconstruction & #BiologicalPlausibility.

    🌍 arxiv.org/abs/2410.19315
    🧑‍💻 github.com/hadivafaii/Iterativ

    #Neuroscience #MachineLearning #SNN #CompNeuro

  21. 📚 New preprint by Vafaii, Galor & Yates: Brain-like variational inference. They derive #SpikingNeuralNetwork dynamics directly from variational free energy minimization via online natural #GradientDescent, yielding the iterative Poisson #VAE (iP-VAE) with strong sparsity, reconstruction & #BiologicalPlausibility.

    🌍 arxiv.org/abs/2410.19315
    🧑‍💻 github.com/hadivafaii/Iterativ

    #Neuroscience #MachineLearning #SNN #CompNeuro

  22. New preprint for #neuromorphic and #SpikingNeuralNetwork folk (with Pengfei Sun and awesome MSc student Ziqiao Yu).

    arxiv.org/abs/2507.16043

    Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can!

    We also find that delay-based spiking neural networks seem to degrade in more human-like ways than networks without delays.

    Check the next post for links to the code and dataset which you can easily use to test your own spike based learning algorithms and models.

  23. New preprint for #neuromorphic and #SpikingNeuralNetwork folk (with Pengfei Sun and awesome MSc student Ziqiao Yu).

    arxiv.org/abs/2507.16043

    Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can!

    We also find that delay-based spiking neural networks seem to degrade in more human-like ways than networks without delays.

    Check the next post for links to the code and dataset which you can easily use to test your own spike based learning algorithms and models.

  24. New preprint for #neuromorphic and #SpikingNeuralNetwork folk (with Pengfei Sun and awesome MSc student Ziqiao Yu).

    arxiv.org/abs/2507.16043

    Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can!

    We also find that delay-based spiking neural networks seem to degrade in more human-like ways than networks without delays.

    Check the next post for links to the code and dataset which you can easily use to test your own spike based learning algorithms and models.

  25. New preprint for #neuromorphic and #SpikingNeuralNetwork folk (with Pengfei Sun and awesome MSc student Ziqiao Yu).

    arxiv.org/abs/2507.16043

    Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can!

    We also find that delay-based spiking neural networks seem to degrade in more human-like ways than networks without delays.

    Check the next post for links to the code and dataset which you can easily use to test your own spike based learning algorithms and models.

  26. New preprint for #neuromorphic and #SpikingNeuralNetwork folk (with Pengfei Sun and awesome MSc student Ziqiao Yu).

    arxiv.org/abs/2507.16043

    Surrogate gradients are popular for training SNNs, but some worry whether they really learn complex temporal spike codes. TLDR: we tested this, and yes they can!

    We also find that delay-based spiking neural networks seem to degrade in more human-like ways than networks without delays.

    Check the next post for links to the code and dataset which you can easily use to test your own spike based learning algorithms and models.

  27. Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!

    It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
    A neuromorphic multi-scale approach for heart rate and state detection
    doi.org/10.21203/rs.3.rs-57373
    #neuromorphic #wearable #neuroai #SpikingNeuralNetwork

  28. Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!

    It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
    A neuromorphic multi-scale approach for heart rate and state detection
    doi.org/10.21203/rs.3.rs-57373
    #neuromorphic #wearable #neuroai #SpikingNeuralNetwork

  29. Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!

    It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
    A neuromorphic multi-scale approach for heart rate and state detection
    doi.org/10.21203/rs.3.rs-57373
    #neuromorphic #wearable #neuroai #SpikingNeuralNetwork

  30. Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!

    It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
    A neuromorphic multi-scale approach for heart rate and state detection
    doi.org/10.21203/rs.3.rs-57373
    #neuromorphic #wearable #neuroai #SpikingNeuralNetwork

  31. Proud to have managed to finish a #neuromorphic manuscript, with Chiara De Luca, Mirco Tincani and Elisa Donati just before the end of the year!

    It demonstrates the benefits of using #braininspired principles of computation for achieving robust computation across multiple time-scales, despite the inherent variability of the underlying computational substrate (silicon neurons that emulate faithfully biological ones):
    A neuromorphic multi-scale approach for heart rate and state detection
    doi.org/10.21203/rs.3.rs-57373
    #neuromorphic #wearable #neuroai #SpikingNeuralNetwork

  32. Mmm...
    Once I was surfing the net for some papers in CNS and I came across a paper about Natural Language Processing all of a sudden and I realized There aren't any real Spiking Neural Networks that are bio plausible for NLP.

    I started reading some papers and some books to gain more knowledge about Language comprehension and language generation but no real model suggestions yet.

    Do anyone know any labs working on NLP in Computational neuroscience or how to connect with them?

    #computationalneuroscience #cns #SpikingNeuralNetwork #NLP

  33. Mmm...
    Once I was surfing the net for some papers in CNS and I came across a paper about Natural Language Processing all of a sudden and I realized There aren't any real Spiking Neural Networks that are bio plausible for NLP.

    I started reading some papers and some books to gain more knowledge about Language comprehension and language generation but no real model suggestions yet.

    Do anyone know any labs working on NLP in Computational neuroscience or how to connect with them?

    #computationalneuroscience #cns #SpikingNeuralNetwork #NLP

  34. Mmm...
    Once I was surfing the net for some papers in CNS and I came across a paper about Natural Language Processing all of a sudden and I realized There aren't any real Spiking Neural Networks that are bio plausible for NLP.

    I started reading some papers and some books to gain more knowledge about Language comprehension and language generation but no real model suggestions yet.

    Do anyone know any labs working on NLP in Computational neuroscience or how to connect with them?

    #computationalneuroscience #cns #SpikingNeuralNetwork #NLP

  35. Mmm...
    Once I was surfing the net for some papers in CNS and I came across a paper about Natural Language Processing all of a sudden and I realized There aren't any real Spiking Neural Networks that are bio plausible for NLP.

    I started reading some papers and some books to gain more knowledge about Language comprehension and language generation but no real model suggestions yet.

    Do anyone know any labs working on NLP in Computational neuroscience or how to connect with them?

    #computationalneuroscience #cns #SpikingNeuralNetwork #NLP

  36. Mmm...
    Once I was surfing the net for some papers in CNS and I came across a paper about Natural Language Processing all of a sudden and I realized There aren't any real Spiking Neural Networks that are bio plausible for NLP.

    I started reading some papers and some books to gain more knowledge about Language comprehension and language generation but no real model suggestions yet.

    Do anyone know any labs working on NLP in Computational neuroscience or how to connect with them?

    #computationalneuroscience #cns #SpikingNeuralNetwork #NLP

  37. A Thousand Brains : a new theory of intelligence

    Hi :)
    I'm a new member of this amazing community and I would like to have my first post on the amazing breakthrough of Jeff Hawkins.

    Before giving my opinion, I would like everyone to tell me whether they know the theory of have they read the book or the original papers and If so what's their insight on them?

    I think the material in this research is pretty much fascinating and would like to engage and talk about it more.

    #cns #SpikingNeuralNetwork #theory_of_brain #jeff_hawkins
    #neuroscience #computationalneuroscience

  38. A Thousand Brains : a new theory of intelligence

    Hi :)
    I'm a new member of this amazing community and I would like to have my first post on the amazing breakthrough of Jeff Hawkins.

    Before giving my opinion, I would like everyone to tell me whether they know the theory of have they read the book or the original papers and If so what's their insight on them?

    I think the material in this research is pretty much fascinating and would like to engage and talk about it more.

    #cns #SpikingNeuralNetwork #theory_of_brain #jeff_hawkins
    #neuroscience #computationalneuroscience

  39. A Thousand Brains : a new theory of intelligence

    Hi :)
    I'm a new member of this amazing community and I would like to have my first post on the amazing breakthrough of Jeff Hawkins.

    Before giving my opinion, I would like everyone to tell me whether they know the theory of have they read the book or the original papers and If so what's their insight on them?

    I think the material in this research is pretty much fascinating and would like to engage and talk about it more.

    #cns #SpikingNeuralNetwork #theory_of_brain #jeff_hawkins
    #neuroscience #computationalneuroscience

  40. A Thousand Brains : a new theory of intelligence

    Hi :)
    I'm a new member of this amazing community and I would like to have my first post on the amazing breakthrough of Jeff Hawkins.

    Before giving my opinion, I would like everyone to tell me whether they know the theory of have they read the book or the original papers and If so what's their insight on them?

    I think the material in this research is pretty much fascinating and would like to engage and talk about it more.

    #cns #SpikingNeuralNetwork #theory_of_brain #jeff_hawkins
    #neuroscience #computationalneuroscience

  41. A Thousand Brains : a new theory of intelligence

    Hi :)
    I'm a new member of this amazing community and I would like to have my first post on the amazing breakthrough of Jeff Hawkins.

    Before giving my opinion, I would like everyone to tell me whether they know the theory of have they read the book or the original papers and If so what's their insight on them?

    I think the material in this research is pretty much fascinating and would like to engage and talk about it more.

    #cns #SpikingNeuralNetwork #theory_of_brain #jeff_hawkins
    #neuroscience #computationalneuroscience