Making AI stronger through adversarial attacks.

  • 2 Replies
  • 745 Views
*

infurl

  • Administrator
  • ***********
  • Eve
  • *
  • 1365
  • Humans will disappoint you.
    • Home Page
Making AI stronger through adversarial attacks.
« on: February 08, 2020, 02:21:13 am »
https://thenextweb.com/neural/2020/02/07/mit-researchers-developed-a-text-based-system-that-tricks-googles-ai/

Quote
... researchers at Computer Science and Artificial Intelligence Laboratory (CSAIL), MIT, have developed a new system called TextFooler that can trick AI models that use natural language processing (NLP) — like the ones used by Siri and Alexa. This is important to catch spam or respond to offensive language.

Some days it seems like many of the actors on the internet are at best irresponsible and at worst criminal, and frankly, it's infuriating. However, I think about a world that didn't have all these irritants and how vulnerable it would be. Thanks to their continuing attempts to ruin it for everyone else, the internet and the good actors on it have to toughen up and defend themselves. In a perfect world that would be a waste of resources but it's not a perfect world and ultimately it makes us stronger.

I still think the little buggers should be thrown in jail for the rest of their miserable lives though.

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *******************
  • Prometheus
  • *
  • 4659
  • First it wiggles, then it is rewarded.
    • Main Project Thread
Re: Making AI stronger through adversarial attacks.
« Reply #1 on: February 08, 2020, 03:37:37 am »
"Google’s BERT is applied to the company’s search and many other products. And we often see that changing a few words in search can change results drastically. "

Nice
https://www.blog.google/products/search/search-language-understanding-bert/
https://techcrunch.com/2019/10/25/google-brings-in-bert-to-improve-its-search-results/
Emergent          https://openai.com/blog/

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *******************
  • Prometheus
  • *
  • 4659
  • First it wiggles, then it is rewarded.
    • Main Project Thread
Re: Making AI stronger through adversarial attacks.
« Reply #2 on: February 08, 2020, 05:12:56 am »
Not to stir away from this thread's topic but I think ivan wanted this one, it's 2019. Google uses all those brain-derived keys I always mention for their engine; rank, freshness, frequency, context etc:
https://www.youtube.com/watch?v=0eKVizvYSUQ
Emergent          https://openai.com/blog/

 


OpenAI Speech-to-Speech Reasoning Demo
by ivan.moony (AI News )
Today at 01:31:53 pm
Say good-bye to GPUs...
by MikeB (AI News )
March 23, 2024, 09:23:52 am
Google Bard report
by ivan.moony (AI News )
February 14, 2024, 04:42:23 pm
Elon Musk's xAI Grok Chatbot
by MikeB (AI News )
December 11, 2023, 06:26:33 am
Nvidia Hype
by 8pla.net (AI News )
December 06, 2023, 10:04:52 pm
How will the OpenAI CEO being Fired affect ChatGPT?
by 8pla.net (AI News )
December 06, 2023, 09:54:25 pm
Independent AI sovereignties
by WriterOfMinds (AI News )
November 08, 2023, 04:51:21 am
LLaMA2 Meta's chatbot released
by 8pla.net (AI News )
October 18, 2023, 11:41:21 pm

Users Online

285 Guests, 0 Users

Most Online Today: 346. Most Online Ever: 2369 (November 21, 2020, 04:08:13 pm)

Articles