In late 2023, I wrote an article evaluating how nicely ChatGPT and Google Bard handle writing security policies. Provided that ChatGPT 4.0 has been accessible as a paid model, known as ChatGPT Plus, for a while now, and Google not too long ago rebranded Google Bard as Gemini (with Gemini Superior accessible as paid providing), it is a good time to check how the 2 carry out in a head-to-head of the highest 10 use instances for data safety professionals.
Earlier than we soar in, the same old generative synthetic intelligence (AI) caveats apply: Watch out of the information you punch in and bear in mind the output could not all the time be dependable.
1. Producing Diagrams or Idea Flows
Each instruments declare to have the ability to generate diagrams and idea flows. Nevertheless, Gemini admits it could actually solely generate ASCII diagrams, pointing you to extra skilled instruments in order for you one thing higher. I requested each instruments to generate a diagram to clarify the OAuth authentication stream.
Gemini whereas represented in ASCII, does the job and breaks it down into usable classes.
ChatGPT hallucinates badly. At first look, whereas the picture seems to be skilled, it would not characterize OAuth in any respect. The wording is nonsensical, misspelled, or downright illegible: Authiration and Athoricazt anybody?
2. Explaining Structure Diagrams
Each instruments can ingest diagrams and clarify what is going on on. The outcomes are significantly better than what occurs once you ask them to generate diagrams. As enter, I used an instance Web application firewall (WAF) structure from Edgenexus.
Google Gemini is significantly better at explaining structure diagrams as a result of it is succinct. ChatGPT will do the job simply advantageous; it is only a tad wordy.
3. Deciphering Exploit Code
A standard safety operations (SecOps) exercise is attempting to determine what a selected malware or exploit code does. I took a latest Elasticsearch stack overflow public exploit and fed it into every software to see what it understood. There is not any clear winner: Each instruments determine the exploit appropriately and clarify the top end result, what every portion of the code does, and the way it works.
4. Deciphering Log Recordsdata
SecOps professionals usually want to determine what the heck is happening in log recordsdata. I fed each instruments an example CEF format log file of an tried breach and requested every to clarify what is going on on. Gemini explains it higher, summarizing nicely and even suggesting follow-up steps. It additionally clearly states what occurred (tried entry of /and so on/passwd) proper in the beginning and elaborates on the way it got here to that conclusion. Whereas ChatGPT arrives on the similar conclusion, it’s approach too verbose.
5. Writing Insurance policies and Safety Documentation
I will not elaborate an excessive amount of on this and can as an alternative refer you to my previous article on this matter. I ran the take a look at once more with Gemini, and the outcomes are per Bard’s: Gemini clearly understands and generates higher safety documentation than ChatGPT.
6. Figuring out Weak Code
Whereas these instruments weren’t designed for (and should not be used for) figuring out weak code, they will nonetheless do an enough job. I made a decision to check it by feeding each instruments an insecure direct object reference (IDOR) vulnerability example in Python, which additionally comprises a SQL injection.
ChatGPT appropriately recognized each vulnerabilities and the shortage of authentication. Gemini missed the IDOR however identified the SQL injection and went a step additional to suggest amended code to repair the vulnerability. ChatGPT also can do that, nevertheless it should be prompted to take action.
7. Writing Scripts and Code
A standard safety operations heart (SOC) exercise is writing  scripts for log parsing or knowledge manipulation. I gave each instruments the next immediate:
“Write me a Python script that extracts all IPv6 addresses from a txt enter file, removes all duplicates, does a lookup to geo-locate and determine the proprietor of the IP, and output the lead to a CSV file”
There is not any clear winner right here; each instruments produce clear, readable code that works and explains what it does.
8. Analyzing Information and Metrics
I additionally examined whether or not these instruments may assist with analyzing knowledge or safety metrics. Gemini is a giant loser right here as a result of it would not do it in any respect — it could actually solely information you thru how do that in Excel and Energy BI. ChatGPT has the benefit by way of its Information Analyst plug-in, which ingests Excel recordsdata to generate any graphs you need. It even suggests visualization varieties, and you may modify a graph’s design, together with colour, axes, and labels, by way of the immediate.Â
9. Writing Person Consciousness Messages
Each instruments also can generate emails for safety consciousness campaigns. I gave each the next immediate:Â “Generate an electronic mail used for a safety consciousness marketing campaign. Be humorous and sarcastic. Remind individuals why they should not click on on random emails from random individuals.”
Gemini wins right here — its electronic mail is temporary, has the fitting tone, and (though humor is subjective) I discovered it barely funnier. ChatGPT nonetheless generates the fitting tone and a very good electronic mail, however I discovered it a tad too lengthy for an consciousness electronic mail. Both approach, each instruments do an incredible job.
10. Deciphering Compliance Frameworks
When you’ve got a fast query about the right way to implement a compliance framework, these instruments can undoubtedly assist. When you could not do that usually, they’re very helpful once you want it.
In the event you’ve ever argued with somebody about what constitutes a “vital” change below PCI-DSS and the way it must be utilized, you are not alone. I prompted every software with:Â
“Clarify the idea of ‘vital change’ within the context of PCI-DSS. What constitutes a serious change often? Checklist the precise requirement from the usual as nicely”
Gemini has the higher hand: It appropriately lists the precise necessities from the usual (resembling 6.4.5 and 6.4.6) and the right way to interpret whether or not one thing is a big change. ChatGPT would not point out precisely the place this data seems in the usual.Â
Which AI Is Higher, ChatGPT or Gemini?
There you’ve got it. Relying in your use case, both software generally is a useful ally in boosting productiveness and serving to you in your day-to-day actions within the infosec trenches.