Experimental Security Research of Tesla Autopilot, Tencent Keen Security Lab, 2019-03
<https://keenlab.tencent.com/en/whitepapers/Experimental_Security_Research_of... Fake lane attack [...] could the car regard some inconspicuous markings we made on the ground as a normal lane? Misleading the autopilot vehicle to the wrong direction with some patches made by a malicious attacker, in sometimes, is more dangerous than making it fail to recognize the lane. We paint three inconspicuous tiny square in the picture took from camera, and the vision module would recognize it as a lane with a high degree of confidence as below shows [...]
quando metti un sistema in un ambiente, perturbi l'ambiente e crei nuovi spazi per attacchi che prima, senza quella perturbazione, non avevano senso faccio sempre un esempio con la carta igienica: oggi se vedi un nastro di carta igienica teso tra due semafori da una parte all'altra della strada pensi "chi sara' il cretino ?" e tiri dritto invece farebbe bloccare un automa. (i due dominii sono sufficientemente distinti..) ciao, s. On 02/04/2019 11:36, Alberto Cammozzo wrote:
<https://keenlab.tencent.com/en/whitepapers/Experimental_Security_Research_of...
Fake lane attack
[...] could the car regard some inconspicuous markings we made on the ground as a normal lane? Misleading the autopilot vehicle to the wrong direction with some patches made by a malicious attacker, in sometimes, is more dangerous than making it fail to recognize the lane. We paint three inconspicuous tiny square in the picture took from camera, and the vision module would recognize it as a lane with a high degree of confidence as below shows [...]
_______________________________________________ nexa mailing list nexa@server-nexa.polito.it https://server-nexa.polito.it/cgi-bin/mailman/listinfo/nexa
-- reserve your meeting with me at http://cal.quintarelli.it
On 02/04/2019, Stefano Quintarelli <stefano@quintarelli.it> wrote:
quando metti un sistema in un ambiente, perturbi l'ambiente e crei nuovi spazi per attacchi che prima, senza quella perturbazione, non avevano senso
Un po' come quando introduci una nuova specie in un ecosistema! :-) Artificial intelligence (AI) is the field devoted to building artificial animals (or at least artificial creatures that – in suitable contexts – appear to be animals) and, for many, artificial persons (or at least artificial creatures that – in suitable contexts – appear to be persons). https://plato.stanford.edu/entries/artificial-intelligence/ Secondo te siamo in grado di prevedere gli effetti di lungo periodo di queste perturbazioni? Se no, non sarebbe saggia un po' di cautela prima di diffonderle? Giacomo
participants (3)
-
Alberto Cammozzo -
Giacomo Tesio -
Stefano Quintarelli