Skip to main content

Questions tagged [artificial-intelligence]

Artificial intelligence (AI), sometimes called machine intelligence, is intelligence demonstrated by machines, especially computer systems. It is the simulation of human intelligence processes. Use this tag for questions about application of AI in Information Security, Securing against AI based attacks, etc...

Filter by
Sorted by
Tagged with
1 vote
0 answers

Detecting “Harvest Now, Decrypt Later” Attacks Using AI/ML Models

I’m researching strategies to detect the “Harvest Now, Decrypt Later” attack, also known as “store now, decrypt later” or “retrospective decryption.” This surveillance approach involves acquiring and ...
2 votes
2 answers

Can modern AI tools provide any information about the true purpose of potentially malicious code?

A recent question of mine was closed, as I effectively requested code analysis. A comment said: If you want an analysis, you could pop it into something like chatgpt Is there any analysis (or ...
2 votes
2 answers

Malware in neural networks

Lately, there has been discussion about malware hidden inside deep neural networks, such as, EvilModel: Hiding Malware Inside of Neural Network Models (pdf). I understand the hiding part, but I would ...
0 votes
0 answers

Impact of Deep Learning Based Flow Correlation on Tor

It's been known ever since Tor existed that flow correlation attacks can break Tor's anonymity, but whereas in the past flow correlation attacks had a false positive rate far too high to be useful ...
1 vote
1 answer

How are generative AIs like ChatGPT jailbroken/reverse engineered?

I've often heard about 'jailbreaking' generative AIs, which is why they're regularly not considered secure ways to generate content. Here's an example of a user jailbreaking a generative AI by ...
35 votes
6 answers

Can a neural network crack hashing algorithms?

I've been reading a bit about neural networks, and their ability to approximate many complex functions. Wouldn't a neural network be capable of cracking a hashing algorithm like SHA256? For example, ...
-1 votes
1 answer

Using Artificial Intelligence (AI) to detect unauthorized code modification to reduce and to even stop zero-day exploits [closed]

Since Solarwinds Hack and Hafnium attack involved some degree of unauthorized code modification (orion DLL, creation of web shell), is it possible to use Artificial Intelligence (AI) built into the ...
2 votes
1 answer

Are there any projects/papers on approaching exploit development with AI/automation?

I'm looking for research on the topic if at all possible or readings about efforts into this. Drilling down into binaries via fuzzing/fingerprinting for known vulnerable binary patterns and a little ...
0 votes
2 answers

What is the current state of author recognition software and what can be done about it?

I'm curious what the current state of author recognition software is, i.e. software that detects the author of a certain anonymous text based on a certain pool of texts obtained from elsewhere. This ...
-3 votes
2 answers

Who is responsible for ensuring that internet users can believe the photos and videos they see online? [closed]

Apologies in advance if this topic is too vague, I wanted to get an idea of peoples' opinions. Technology now exists that makes photography a unreliable medium in terms of truth. Image and video ...
3 votes
1 answer

What is "Intentionally misleading Artificial Intelligence to create a misleading outcome" called?

I'm writing about a computer system that relies on Artificial Intelligence and the threats that this may include. One threat vector (for example) is to seed Bayesian AI with content to skew the ...
1 vote
1 answer

What would be an example of 'AI' in your average security appliance?

It seems that more and more Anti-Virus and other security related business solutions are adding the 'AI' and 'machine learning' buzzwords to their marketing repertoire. However, the only 'AI' I ever ...
2 votes
0 answers

Measuring real effectiveness of Machine Learning based IDS [closed]

I am currently investigation effectiveness of Intrusion Detection/Prevention Systems that are backed my Machine Learning rather than traditional Signature based detection mechanisms, so that the ...