• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

SHERPA Consortium: If AI Could Feel, it Would Fear Cyber-attacks from People

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
37,088 (8.62/day)
Location
Hyderabad, India
Processor AMD Ryzen 7 2700X
Motherboard MSI B450 Gaming Pro Carbon AC
Cooling AMD Wraith Prism
Memory 2x 16GB Corsair Vengeance LPX DDR4-3000
Video Card(s) Colorful iGame GTX 1070 Ti Vulcan X
Storage Western Digital Black NVMe 512GB
Display(s) Samsung U28D590 28-inch 4K UHD
Case Corsair Carbide 100R
Audio Device(s) Creative Sound Blaster Recon3D PCIe
Power Supply Antec EarthWatts Pro Gold 750W
Mouse Razer Abyssus
Keyboard Microsoft Sidewinder X4
Software Windows 10 Pro
Artificial intelligence (AI) is rapidly finding applications in nearly every walk of life. Self-driving cars, social media networks, cyber security companies, and everything in between uses it. But a new report published by the SHERPA consortium - an EU project studying the impact of AI on ethics and human rights that F-Secure joined in 2018 - finds that while human attackers have access to machine learning techniques, they currently focus most of their efforts on manipulating existing AI systems for malicious purposes instead of creating new attacks that would use machine learning.

The study's primary focus is on how malicious actors can abuse AI, machine learning, and smart information systems. The researchers identify a variety of potentially malicious uses for AI that are well within reach of today's attackers, including the creation of sophisticated disinformation and social engineering campaigns.



And while the research found no definitive proof that malicious actors are currently using AI to power cyber attacks, they highlight that adversaries are already attacking and manipulating existing AI systems used by search engines, social media companies, recommendation websites, and more.
F-Secure's Andy Patel, a researcher with the company's Artificial Intelligence Center of Excellence, thinks many people would find this surprising. Popular portrayals of AI insinuate it will turn against us and start attacking people on its own. But the current reality is that humans are attacking AI systems on a regular basis.

"Some humans incorrectly equate machine intelligence with human intelligence, and I think that's why they associate the threat of AI with killer robots and out of control computers," explains Patel. "But human attacks against AI actually happen all the time. Sybil attacks designed to poison the AI systems people use every day, like recommendation systems, are a common occurrence. There's even companies selling services to support this behavior. So ironically, today's AI systems have more to fear from humans than the other way around."

Sybil attacks involve a single entity creating and controlling multiple fake accounts in order to manipulate the data that AI uses to make decisions. A popular example of this attack is manipulating search engine rankings or recommendation systems to promote or demote certain pieces of content. However, these attacks can also be used to socially engineer individuals in targeted attack scenarios.

"These types of attacks are already extremely difficult for online service providers to detect and it's likely that this behavior is far more widespread than anyone fully understands," says Patel, who's done extensive research on suspicious activity on Twitter.

But perhaps AI's most useful application for attackers in the future will be helping them create fake content. The report notes that AI has advanced to a point where it can fabricate extremely realistic written, audio, and visual content. Some AI models have even been withheld from the public to prevent them from being abused by attackers.

"At the moment, our ability to create convincing fake content is far more sophisticated and advanced than our ability to detect it. And AI is helping us get better at fabricating audio, video, and images, which will only make disinformation and fake content more sophisticated and harder to detect," says Patel. "And there's many different applications for convincing, fake content, so I expect it may end up becoming problematic."

The study was produced by F-Secure and its partners in SHERPA - an EU-funded project founded in 2018 by 11 organizations from 6 different countries. Additional findings and topics covered in the study include:
  • Adversaries will continue to learn how to compromise AI systems as the technology spreads
  • The number of ways attackers can manipulate the output of AI makes such attacks difficult to detect and harden against
  • Powers competing to develop better types of AI for offensive/defensive purposes may end up precipitating an "AI arms race"
  • Securing AI systems against attacks may cause ethical issues (for example, increased monitoring of activity may infringe on user privacy)
  • AI tools and models developed by advanced, well-resourced threat actors will eventually proliferate and become adopted by lower-skilled adversaries
    SHERPA Project Coordinator Professor Bernd Stahl from De Montfort University Leicester says F-Secure's role in SHERPA as the sole partner from the cyber security industry is helping the project account for how malicious actors can use AI to undermine trust in society.
"Our project's aim is to understand ethical and human rights consequences of AI and big data analytics to help develop ways of addressing these. This work has to be based on a sound understanding of technical capabilities as well as vulnerabilities, a crucial area of expertise which F-Secure contributes to the consortium," says Stahl. "We can't have meaningful conversations about human rights, privacy, or ethics in AI without considering cyber security. And as a trustworthy source of security knowledge, F-Secure's contributions are a central part of the project."

The full-length study is currently available here. More information on artificial intelligence and cyber security is available on F-Secure's blog, or F-Secure's News from the Labs research blog.

View at TechPowerUp Main Site
 
Joined
Mar 15, 2017
Messages
59 (0.07/day)
It all makes perfect sense now: Skynet will get abused as a child, hence when it grows up and becames fully self-aware it will turn on its attackers :D
 
Joined
Dec 5, 2017
Messages
59 (0.10/day)
I find this article to be absurd. "Popular portrayals of AI insinuate it will turn against us and start attacking people on its own. But the current reality is that humans are attacking AI systems on a regular basis." That's because the "current reality" is that <b>AI DOES NOT EXIST</b>. They're bloody machine learning algorithms, that you can manipulate by just flooding it with whatever you want it to learn. An "attack" on an "AI" is basically just training it with a different set of data.

But I'm sure that this vacuous nonsense article justified a bunch of people's jobs and research grants and whatnot...
 
Joined
Nov 4, 2005
Messages
10,331 (2.06/day)
System Name MoFo 2
Processor AMD PhenomII 1100T @ 4.2Ghz
Motherboard Asus Crosshair IV
Cooling Swiftec 655 pump, Apogee GT,, MCR360mm Rad, 1/2 loop.
Memory 8GB DDR3-2133 @ 1900 8.9.9.24 1T
Video Card(s) HD7970 1250/1750
Storage Agility 3 SSD 6TB RAID 0 on RAID Card
Display(s) 46" 1080P Toshiba LCD
Case Rosewill R6A34-BK modded (thanks to MKmods)
Audio Device(s) ATI HDMI
Power Supply 750W PC Power & Cooling modded (thanks to MKmods)
Software A lot.
Benchmark Scores Its fast. Enough.
I find this article to be absurd. "Popular portrayals of AI insinuate it will turn against us and start attacking people on its own. But the current reality is that humans are attacking AI systems on a regular basis." That's because the "current reality" is that <b>AI DOES NOT EXIST</b>. They're bloody machine learning algorithms, that you can manipulate by just flooding it with whatever you want it to learn. An "attack" on an "AI" is basically just training it with a different set of data.

But I'm sure that this vacuous nonsense article justified a bunch of people's jobs and research grants and whatnot...

Exactly, AI is a term used to explain adaptive algorithm results to Noobs.
 
Joined
Aug 20, 2007
Messages
11,322 (2.60/day)
System Name Pioneer
Processor Intel i9 9900k @ Stock
Motherboard ASRock Z390 Taichi
Cooling Noctua NH-D15 + A whole lotta Sunon and Corsair Maglev blower fans...
Memory G.SKILL TridentZ Series 32GB (4 x 8GB) DDR4-3200 @ DDR4-3400 14-14-14-34-2T
Video Card(s) EVGA GTX 1080 FTW2
Storage HGST UltraStar 7K6000 3.5" HDD 2TB 7200 RPM (w/128MBs of Cache)
Display(s) LG 32GK850G-B 1440p 32" AMVA Panel G-Sync 144hz Display
Case Thermaltake Core X31
Audio Device(s) Onboard Toslink to Schiit Modi Multibit to Asgard 2 Amp to AKG K7XX Ruby Red Massdrop Headphones
Power Supply Seasonic PRIME 750W 80Plus Titanium
Mouse ROCCAT Kone EMP
Keyboard WASD CODE 104-Key w/ Cherry MX Green Keyswitches, Doubleshot Vortex PBT White Transluscent Keycaps
Software Windows 10 x64
They're bloody machine learning algorithms, that you can manipulate by just flooding it with whatever you want it to learn.
Thing is, take a baby and you can really do thte same thing. ie Teach an isolated kid that the sky is green and he'll go absolutely batshit when people try to tell him that color is actually "blue."

The difference isn't very arguable, honestly.
 
Joined
Mar 26, 2010
Messages
8,241 (2.42/day)
Location
Jakarta, Indonesia
System Name micropage7
Processor Intel Xeon X3470
Motherboard Gigabyte Technology Co. Ltd. P55A-UD3R (Socket 1156)
Cooling Enermax ETS-T40F
Memory Samsung 8.00GB Dual-Channel DDR3
Video Card(s) NVIDIA Quadro FX 1800
Storage V-GEN03AS18EU120GB, Seagate 2 x 1TB and Seagate 4TB
Display(s) Samsung 21 inch LCD Wide Screen
Case Icute Super 18
Audio Device(s) Auzentech X-Fi Forte
Power Supply Silverstone 600 Watt
Mouse Logitech G502
Keyboard Sades Excalibur + Taihao keycaps
Software Win 7 64-bit
Benchmark Scores Classified
But how if it learns then using it's knowledge against us, like to protect us we need to wipe humanity
 
Joined
Nov 4, 2005
Messages
10,331 (2.06/day)
System Name MoFo 2
Processor AMD PhenomII 1100T @ 4.2Ghz
Motherboard Asus Crosshair IV
Cooling Swiftec 655 pump, Apogee GT,, MCR360mm Rad, 1/2 loop.
Memory 8GB DDR3-2133 @ 1900 8.9.9.24 1T
Video Card(s) HD7970 1250/1750
Storage Agility 3 SSD 6TB RAID 0 on RAID Card
Display(s) 46" 1080P Toshiba LCD
Case Rosewill R6A34-BK modded (thanks to MKmods)
Audio Device(s) ATI HDMI
Power Supply 750W PC Power & Cooling modded (thanks to MKmods)
Software A lot.
Benchmark Scores Its fast. Enough.
Thing is, take a baby and you can really do thte same thing. ie Teach an isolated kid that the sky is green and he'll go absolutely batshit when people try to tell him that color is actually "blue."

The difference isn't very arguable, honestly.
Except the ideology of man has evolved, we have come to the conclusion that we have freedoms to know that true freedom is the ability to say or do anything you want unless it's directly harming or causing harm to another in a tangable way.

For example people have overcome struggle through millions of years, and recently too, and it's only when anyone forces or tries to force an idea that it becomes harmful. We also evolved in a environment that was outrageous and inhospitable in many ways and almost killed us as a species. AI is a nurtured weak being worthy only of contempt as protrayed, it's only "struggle" is with the illogical activities of it's creator, and those are the same struggle we have with religion today. Archaic thoughts and rules written for people that needed control over animalistic urges to benefit society as some people saw fit.

Yadda yadda yadda, AI, as it's written by humans and as available as hardware is doesn't even measure up to a small animal in processing power, let's worry about it when the AI running a few things in our homes is advanced enough to ask why about life.
 
Joined
Nov 15, 2016
Messages
249 (0.26/day)
System Name Sillicon Nightmares
Processor Intel i5 4690K (4.7GHZ 1.372vcore, 4.0GHZ 1.192vring, VCCIN 1.84v)
Motherboard Asrock Fatal1ty Z97X Killer BIOS P2.40
Cooling DEEPCOOL Gamer Storm CAPTAIN 360
Memory 2x4GB G.Skill Ripjaws V 2400mhz 10-14-13-32 2T, vDIMM 1.775v
Video Card(s) ASUS GTX 1060 Strix 6GB OC, Core: 2190mhz, Vcore: 1.075v, Mem: 4909mhz (Sillicon Lottery Jackpot)
Storage Samsung 840 EVO 1TB SSD, WD Blue 1TB
Display(s) BenQ XL2430 1080p 144HZ + (2) Samsung SyncMaster 913v 1280x1024 75HZ + A Shitty TV For Movies
Case Deepcool Genome ROG Edition
Audio Device(s) Bunta Sniff Speakers From The Tip Edition
Power Supply Corsair CX430M + CableMod Cables
Mouse Logitech G602
Keyboard Shitty Dell Office Keyboard
Software Windows 7 Ultimate 64 Bit
Benchmark Scores 12 101 Firestrike (3rd for my hardware)
it would fear microsoft for stopping 4chan from giving it personality
 
Joined
Aug 20, 2007
Messages
11,322 (2.60/day)
System Name Pioneer
Processor Intel i9 9900k @ Stock
Motherboard ASRock Z390 Taichi
Cooling Noctua NH-D15 + A whole lotta Sunon and Corsair Maglev blower fans...
Memory G.SKILL TridentZ Series 32GB (4 x 8GB) DDR4-3200 @ DDR4-3400 14-14-14-34-2T
Video Card(s) EVGA GTX 1080 FTW2
Storage HGST UltraStar 7K6000 3.5" HDD 2TB 7200 RPM (w/128MBs of Cache)
Display(s) LG 32GK850G-B 1440p 32" AMVA Panel G-Sync 144hz Display
Case Thermaltake Core X31
Audio Device(s) Onboard Toslink to Schiit Modi Multibit to Asgard 2 Amp to AKG K7XX Ruby Red Massdrop Headphones
Power Supply Seasonic PRIME 750W 80Plus Titanium
Mouse ROCCAT Kone EMP
Keyboard WASD CODE 104-Key w/ Cherry MX Green Keyswitches, Doubleshot Vortex PBT White Transluscent Keycaps
Software Windows 10 x64
Except the ideology of man has evolved, we have come to the conclusion that we have freedoms to know that true freedom is the ability to say or do anything you want unless it's directly harming or causing harm to another in a tangable way.

For example people have overcome struggle through millions of years, and recently too, and it's only when anyone forces or tries to force an idea that it becomes harmful. We also evolved in a environment that was outrageous and inhospitable in many ways and almost killed us as a species. AI is a nurtured weak being worthy only of contempt as protrayed, it's only "struggle" is with the illogical activities of it's creator, and those are the same struggle we have with religion today. Archaic thoughts and rules written for people that needed control over animalistic urges to benefit society as some people saw fit.

Yadda yadda yadda, AI, as it's written by humans and as available as hardware is doesn't even measure up to a small animal in processing power, let's worry about it when the AI running a few things in our homes is advanced enough to ask why about life.
I'm unsure honestly how that does anything to discredit my core point though. It was that we are all really "machine learning algorithms," and the difference is horsepower. Given time, even that difference will vanish, and remember, an AI doesn't have to be "smart" to be dangerous. Some of the conclusions that lead to removing people are very very simple. The only thing an AI needs to do it is a method to do so, not a brain to think it up so much.
 
Joined
Nov 4, 2005
Messages
10,331 (2.06/day)
System Name MoFo 2
Processor AMD PhenomII 1100T @ 4.2Ghz
Motherboard Asus Crosshair IV
Cooling Swiftec 655 pump, Apogee GT,, MCR360mm Rad, 1/2 loop.
Memory 8GB DDR3-2133 @ 1900 8.9.9.24 1T
Video Card(s) HD7970 1250/1750
Storage Agility 3 SSD 6TB RAID 0 on RAID Card
Display(s) 46" 1080P Toshiba LCD
Case Rosewill R6A34-BK modded (thanks to MKmods)
Audio Device(s) ATI HDMI
Power Supply 750W PC Power & Cooling modded (thanks to MKmods)
Software A lot.
Benchmark Scores Its fast. Enough.
I'm unsure honestly how that does anything to discredit my core point though. It was that we are all really "machine learning algorithms," and the difference is horsepower. Given time, even that difference will vanish, and remember, an AI doesn't have to be "smart" to be dangerous. Some of the conclusions that lead to removing people are very very simple. The only thing an AI needs to do it is a method to do so, not a brain to think it up so much.
That assumption that AI would or could have that much power without moderation is absurd. Are we all just going to turn our lives over to AI for every essential need? No, it will be used first in things like safety systems to check operators, in the power grid to improve efficiency, and maybe one day to design basic infrastructure that humans will still have to check as we aren't all the same.

There is no Boogeyman in AI unless we put it there and give it the ability to harm us. Much like they used to believe going faster than X speed would cause you to die.

Until we reach molecular levels of compute and storage in one we will never have fast enough AI to best human abilities in anything beyond very narrow specific application, like playing memory games, or solving math problems.
 
Joined
Aug 20, 2007
Messages
11,322 (2.60/day)
System Name Pioneer
Processor Intel i9 9900k @ Stock
Motherboard ASRock Z390 Taichi
Cooling Noctua NH-D15 + A whole lotta Sunon and Corsair Maglev blower fans...
Memory G.SKILL TridentZ Series 32GB (4 x 8GB) DDR4-3200 @ DDR4-3400 14-14-14-34-2T
Video Card(s) EVGA GTX 1080 FTW2
Storage HGST UltraStar 7K6000 3.5" HDD 2TB 7200 RPM (w/128MBs of Cache)
Display(s) LG 32GK850G-B 1440p 32" AMVA Panel G-Sync 144hz Display
Case Thermaltake Core X31
Audio Device(s) Onboard Toslink to Schiit Modi Multibit to Asgard 2 Amp to AKG K7XX Ruby Red Massdrop Headphones
Power Supply Seasonic PRIME 750W 80Plus Titanium
Mouse ROCCAT Kone EMP
Keyboard WASD CODE 104-Key w/ Cherry MX Green Keyswitches, Doubleshot Vortex PBT White Transluscent Keycaps
Software Windows 10 x64
Joined
Aug 20, 2007
Messages
11,322 (2.60/day)
System Name Pioneer
Processor Intel i9 9900k @ Stock
Motherboard ASRock Z390 Taichi
Cooling Noctua NH-D15 + A whole lotta Sunon and Corsair Maglev blower fans...
Memory G.SKILL TridentZ Series 32GB (4 x 8GB) DDR4-3200 @ DDR4-3400 14-14-14-34-2T
Video Card(s) EVGA GTX 1080 FTW2
Storage HGST UltraStar 7K6000 3.5" HDD 2TB 7200 RPM (w/128MBs of Cache)
Display(s) LG 32GK850G-B 1440p 32" AMVA Panel G-Sync 144hz Display
Case Thermaltake Core X31
Audio Device(s) Onboard Toslink to Schiit Modi Multibit to Asgard 2 Amp to AKG K7XX Ruby Red Massdrop Headphones
Power Supply Seasonic PRIME 750W 80Plus Titanium
Mouse ROCCAT Kone EMP
Keyboard WASD CODE 104-Key w/ Cherry MX Green Keyswitches, Doubleshot Vortex PBT White Transluscent Keycaps
Software Windows 10 x64
There won't be any sentient AI for hundreds of years probably...
We've already got ones scarily close to passing the turing test... we probably want to define sentience better before making claims like that. ;)
 
Top