Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Questions tagged [ai-security]

For questions about the security measures against malicious algorithms, and security measures provided by AI algorithms in detecting, mitigating and preventing breaches and malicious activity.

Security is freedom from, or resilience against, potential harm (or other unwanted coercive change) from external forces. Beneficiaries (technically referents) of security may be persons and social groups, objects and institutions, ecosystems, and any other entity or phenomenon vulnerable to unwanted change by its environment.

19 questions
31
votes
7 answers

Is artificial intelligence vulnerable to hacking?

The paper The Limitations of Deep Learning in Adversarial Settings explores how neural networks might be corrupted by an attacker who can manipulate the data set that the neural network trains with. The authors experiment with a neural network meant…
Surya Sg
  • 495
  • 4
  • 13
28
votes
8 answers

Is there any research on the development of attacks against artificial intelligence systems?

Is there any research on the development of attacks against artificial intelligence systems? For example, is there a way to generate a letter "A", which every human being in this world can recognize but, if it is shown to the state-of-the-art…
Lion Lai
  • 423
  • 4
  • 9
11
votes
2 answers

What tools are used to deal with adversarial examples problem?

The problem of adversarial examples is known to be critical for neural networks. For example, an image classifier can be manipulated by additively superimposing a different low amplitude image to each of many training examples that looks like noise…
Ilya Palachev
  • 299
  • 2
  • 11
9
votes
1 answer

How would one debug, understand or fix the outcome of a neural network?

It seems fairly uncontroversial to say that NN based approaches are becoming quite powerful tools in many AI areas - whether recognising and decomposing images (faces at a border, street scenes in automobiles, decision making in uncertain/complex…
Stilez
  • 233
  • 1
  • 4
7
votes
1 answer

What will happen when you place a fake speedsign on a highway?

I was wondering what will happen when somebody places a fake speedsign, of 10 miles per hour on a high way. Will a autonomous car slow down? Is this a current issue of autonomous cars?
Eddy
  • 81
  • 2
6
votes
1 answer

During neural network training, can gradients leak sensitive information in case training data fed is encrypted (homomorphic)?

Some algorithms in the literature allow recovering the input data used to train a neural network. This is done using the gradients (updates) of weights, such as in Deep Leakage from Gradients (2019) by Ligeng Zhu et al. In case the neural network is…
witdev
  • 73
  • 4
6
votes
3 answers

Why did a Tesla car mistake a truck with a bright sky?

Do we know why Tesla's autopilot mistaken empty sky with a high-sided lorry which resulted in fatal crash involving a car in self-drive mode? Was it AI fault or something else? Is there any technical explanation behind this why this happened? The…
kenorb
  • 10,423
  • 3
  • 43
  • 91
5
votes
2 answers

Can artificial intelligence applications be hacked?

Can artificial intelligence (or machine learning) applications or agents be hacked, given that they are software applications, or are all AI applications secure?
ME.
  • 115
  • 1
  • 6
5
votes
1 answer

Which problems in information security can be solved better using neural networks?

Information security has become a thriving field during the last years. It is a broad domain ranging from planing and building over testing to operating different applications, systems and networks in a secure fashion. From small embedded systems to…
Demento
  • 1,684
  • 1
  • 7
  • 26
4
votes
1 answer

How to design a classifier while the patterns of positive data are changing rapidly?

In some situation, like risk detection and spam detection. The pattern of Good User is stable, while the patterns of Attackers are changing rapidly. How can I make a model for that? Or which classifier/method should I use?
Yang
  • 143
  • 4
4
votes
2 answers

Which government agencies oversee development of new AI?

Nick Bostrom talks in his book Superintelligence about the many dangers of AI. He considers it necessary that strong security mechanisms are put in place to ensure that a machine, once it gains general intelligence far beyond human capabilities,…
Demento
  • 1,684
  • 1
  • 7
  • 26
2
votes
2 answers

Could a CNN hear the difference between sound of a pet moving, and a person?

"Deep Learning" neural networks are now successful at image-recognition tasks that I would not have expected say 10 years ago. I wonder if the current state of the art in machine learning could generally tell the difference between the sound of a…
user3732008
  • 31
  • 3
2
votes
0 answers

To perform a white-box adversarial attack, would the use of a numerical gradient suffice?

I am trying to perform a white-box attack on a model. Would it be possible to simply use the numerical gradient of the output wrt input directly rather than computing each subgradient of the network analytically? Would this (1) work and (2) actually…
FeedMeInformation
  • 327
  • 1
  • 7
2
votes
1 answer

How can genetic programming be used to prevent cyberterrorism?

I've read on wiki that genetic programming has 'outstanding results' in cyberterrorism prevention. Further more, this abstract says: Using machine-coded linear genomes and a homologous crossover operator in genetic programming, promising results…
kenorb
  • 10,423
  • 3
  • 43
  • 91
1
vote
1 answer

How to source training data in ML for information security?

A company entrusts a Data Scientist with the mission of processing and valuing data for the research or treatment of events related to traces of computer attacks. I was wondering how would he get the train data. I guess he would need to exploit the…
Revolucion for Monica
  • 210
  • 1
  • 7
1
2