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
0 votes
0 answers

How to Measure the Impact of Adding a Translation Layer to Large Language Models?

I'm currently exploring the integration of a translation layer into Large Language Models (LLMs) to preprocess all inputs into a uniform language (English) before processing by the model. The idea is ...
Ilya Gazman's user avatar
2 votes
1 answer

Is it possible to detect image manipulation, for example deep fakes?

Is it possible to detect image manipulation, for example deep fakes? I will publish some photos on internet, and want others to be able to verify if photos are really from me, and also to detect if ...
Qsig's user avatar
  • 29
2 votes
1 answer

Why do adversarial attack transfer well?

I have read (*) that a common technique to attack a black box AI system based on a neural network is to use it to train a surrogate model to make the same classifications as the black box one. Once ...
Weier's user avatar
  • 131
0 votes
1 answer

Retaining document level security of a CMS

I am responsible for a CMS that contains a lot of documents with knowledge and these documents are protected so not everyone can see them. Now we are tasked to find a technology partner who helps us &...
Marged's user avatar
  • 101
1 vote
2 answers

Is it possible to have a ChatGPT bot that can answer questions about sensitive information without using external servers?

We have a lot of internal documentation that contains sensitive information. Is it possible to have a ChatGPT bot that can answer questions about this information, to my used by users with clearance ...
BanksySan's user avatar
  • 111
0 votes
1 answer

Real Case Attack on AI model

There are so many papers showing the vulnerability of some AI/ML models. I read some of them only demonstrate their attack to a model "in the lab". Are those attacks really feasible in real-...
malioboro's user avatar
  • 2,819
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 ...
Revolucion for Monica's user avatar
0 votes
0 answers

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 ...
Denis Leonov's user avatar
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) ...
witdev's user avatar
  • 73
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 ...
FeedMeInformation's user avatar
29 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 ...
Lion Lai's user avatar
  • 433
1 vote
1 answer

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?
55597's user avatar
  • 71
5 votes
2 answers

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?
ME.'s user avatar
  • 115
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 ...
Yang's user avatar
  • 143
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 ...
Ilya Palachev's user avatar
31 votes
7 answers

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. ...
Surya Sg's user avatar
  • 495
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 ...
user3732008's user avatar
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 ...
Demento's user avatar
  • 1,684
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 ...
Demento's user avatar
  • 1,684
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 ...
Stilez's user avatar
  • 233
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's user avatar
  • 81
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 ...
kenorb's user avatar
  • 10.5k
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 ...
kenorb's user avatar
  • 10.5k