2022 Developer Survey is open! Take survey.

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.

Filter by
Sorted by
Tagged with
1 vote
1 answer
35 views

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 ...
user avatar
0 votes
0 answers
39 views

Is there any research work on known malware detection systems based on AI?

I'm working on writing an article about the possibilities of modern AI-based algorithms to produce invisible self-learning malware, that can distribute itself throughout the internet and create ...
user avatar
6 votes
1 answer
123 views

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) ...
user avatar
  • 73
2 votes
0 answers
37 views

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 ...
user avatar
26 votes
8 answers
4k views

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 ...
user avatar
  • 403
1 vote
1 answer
72 views

How do I encrypt and decrypt my model when I run inference on it?

I want my models to be accessible only by my programs. How do I encrypt and decrypt my model when I run inference on it? Is there any existing technology that is widely used?
user avatar
  • 71
5 votes
2 answers
451 views

Can artificial intelligence applications be hacked? [duplicate]

Can artificial intelligence (or machine learning) applications or agents be hacked, given that they are software applications, or are all AI applications secure?
user avatar
  • 115
4 votes
1 answer
42 views

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 ...
user avatar
  • 143
10 votes
2 answers
583 views

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 ...
user avatar
30 votes
7 answers
5k views

Is artificial intelligence vulnerable to hacking? [closed]

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. ...
user avatar
  • 485
2 votes
2 answers
474 views

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 ...
user avatar
6 votes
1 answer
129 views

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 ...
user avatar
  • 1,652
4 votes
2 answers
153 views

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 ...
user avatar
  • 1,652
9 votes
1 answer
238 views

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 ...
user avatar
  • 233
6 votes
1 answer
269 views

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?
user avatar
  • 71
2 votes
1 answer
89 views

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 ...
user avatar
  • 10k
6 votes
3 answers
1k views

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 ...
user avatar
  • 10k