The nightmare scenario for computer security - artificial intelligence programs that can learn how to evade even the best defenses - may already have arrived.
That warning from security researchers is driven home by a team from IBM Corp. who have used the artificial intelligence technique known as machine learning to build hacking programs that could slip past top-tier defensive measures. The group will unveil details of its experiment at the Black Hat security conference in Las Vegas on Wednesday.
State-of-the-art defenses generally rely on examining what the attack software is doing, rather than the more commonplace technique of analyzing software code for danger signs. But the new genre of AI-driven programs can be trained to stay dormant until they reach a very specific target, making them exceptionally hard to stop.
No one has yet boasted of catching any malicious software that clearly relied on machine learning or other variants of artificial intelligence, but that may just be because the attack programs are too good to be caught.
More here
DelMarVa's Premier Source for News, Opinion, Analysis, and Human Interest Contact Publisher Joe Albero at alberobutzo@wmconnect.com or 410-430-5349
1 comment:
And here you all think this is the next best thing since sliced bread... You will see the dangers soon enough, and if you want a good glimps of just the minor capabilities this will have?? Then watch one of 3 movies, The Eagle Eye with shia labeouf and the movie with tom cruise called minority report, and the movie called terminator where they have skynet and it launches nukes and kills a lot of people... The govt already has a program called skynet, they already have AI and continue to work with it, just shorty after creating AI programs, they felt threatened and developed their own language to communicate so we couldn't stop them or shut them down...
Crazy as it is, you all will see soon enough that the new tech from here on out is considered the mark of the beast...
Post a Comment