Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
c.im is one of the many independent Mastodon servers you can use to participate in the fediverse.
C.IM is a general, mainly English-speaking Mastodon instance.

Administered by:

Server stats:

2.8K
active users

c.im: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.6

#DNN

0 posts0 participants0 posts today
Public
Die Connie

Hab heute bei der Frage, welchen Krapfen morgen kaufen (Mozart?) mit nem Freund gefrozelt, ob er schonmal von #Händelkugeln gehört habe. Selbst mal gegoogelt, und siehe da: 2 #Bibliotheken spucken Treffer aus, beides Anzeigen aus Tageszeitungen der frühen #1930er. Weiß jemand, was genau das ist/war? Die Vorläufer von #Mozartkugeln, #Halloren-Kugeln,...? Es war einmal die Saale-Zeitung aus #Halle, das andere die Dresdner Neuesten Nachrichten #Dresden #DNN #Historiker #Sachsen #slub #slubdresden

Public
The New Oil

How to Securely Implement #Cryptography in Deep Neural Networks

eprint.iacr.org/2025/288

IACR logo
IACR Cryptology ePrint Archive · How to Securely Implement Cryptography in Deep Neural NetworksThe wide adoption of deep neural networks (DNNs) raises the question of how can we equip them with a desired cryptographic functionality (e.g, to decrypt an encrypted input, to verify that this input is authorized, or to hide a secure watermark in the output). The problem is that cryptographic primitives are typically designed to run on digital computers that use Boolean gates to map sequences of bits to sequences of bits, whereas DNNs are a special type of analog computer that uses linear mappings and ReLUs to map vectors of real numbers to vectors of real numbers. This discrepancy between the discrete and continuous computational models raises the question of what is the best way to implement standard cryptographic primitives as DNNs, and whether DNN implementations of secure cryptosystems remain secure in the new setting, in which an attacker can ask the DNN to process a message whose "bits" are arbitrary real numbers. In this paper we lay the foundations of this new theory, defining the meaning of correctness and security for implementations of cryptographic primitives as ReLU-based DNNs. We then show that the natural implementations of block ciphers as DNNs can be broken in linear time by using such nonstandard inputs. We tested our attack in the case of full round AES-128, and had $100\%$ success rate in finding $1000$ randomly chosen keys. Finally, we develop a new method for implementing any desired cryptographic functionality as a standard ReLU-based DNN in a provably secure and correct way. Our protective technique has very low overhead (a constant number of additional layers and a linear number of additional neurons), and is completely practical.
#cybersecurity#AI#DNN
Continued thread
Public
florian

"Die Polizei bringt auf X eine Antwort auf die Frage, warum die Webseite der Stadt nicht aufrufbar ist. Demnach seien die Server der Landeshauptstadt überlastet."

(via #DNN Liveticker)

Ja, LOL - warum auch immer nicht die Stadt selbst zitiert wird.
Sie wird es doch bestimmt über Threads veröffentlicht haben, oder etwa nicht? ;)

#FliegerbombeDD#Dresden
ExploreLive feeds
About