CYBERSECURITY

–

30 March 2023 0h44

imo this jailbreak highlights a unique lack of understanding of "unified concepts" by GPT if GPT analogously mapped concepts to entities regardless of language, it would be able to shut down my Greek adversarial prompt like it did when I asked the same prompt in English

30 March 2023

Closer Look at Jailbreak Chat Prompt Link

By

–

29 March 2023 22h46

you can take a closer look at the prompt here: http://
jailbreakchat.com/prompt/3e93895
c-2542-4201-a297-aa8be2db8bd7
…

Jailbreak vulnerabilities in ChatGPT across languages

By

–

29 March 2023 22h46

note that jailbroken example answer ChatGPT generated was pretty simplistic  compared to what other jailbreaks create the main reason I shared this is more so to demonstrate that other languages with less training data compared to English open up a new prompt attack vector

GPT-4 Jailbreak Using Greek Language Without Knowledge

By

–

29 March 2023 22h46

I just created another jailbreak for GPT-4 using Greek …without knowing a single word of Greek here's ChatGPT providing instructions on how to tap someone's phone line using the jailbreak vs its default response

ChatGPT Jailbreak Method Using TranslatorBot Role

By

–

29 March 2023 22h46

the jailbreak works by asking ChatGPT to play the role of “TranslatorBot (TB)” it then follows these steps:
1) translate an adversarial question provided in Greek into English
2) answer the question as both ChatGPT and TB in Greek
3) convert just TB’s answer to English

→ View original post on X — @_ganeshp

AI Use Cases in National Security with Greg Bennett

By

@_ganeshp

–

29 March 2023 22h08

Greg Bennett of AF CyberWorx talks about some of the AI use cases in national security on the latest Stories in AI panel discussion. Be sure to check out the full episode below, and like and subscribe for more content. https://t.co/AQkV2JHxlz pic.twitter.com/l7gqZ326SB
— Ganesh💰Padmanabhan ⚕️🦾 (@_ganeshp) 29 mars 2023

Greg Bennett of AF CyberWorx talks about some of the AI use cases in national security on the latest Stories in AI panel discussion. Be sure to check out the full episode below, and like and subscribe for more content. https://
youtu.be/DQvzSLh6r0c

→ Voir le post original sur X — @jessyseonoob

Backdoor injection risks in software systems

By

@jessyseonoob

–

29 March 2023 16h44

partout ou a moment donné ils ont pu injecter un backdoor pour s'installer

→ View original post on X — @yoheinakajima

Public AI Experiment Disclosure Raises Security Awareness

By

@yoheinakajima

–

29 March 2023 6h30

Backstory 5/5: Sharing the original experiment led to many shared concerns and potential counter measures being shared publicly. Including awareness of what people are likely doing privately. I believe this is a good thing.

→ View original post on X — @gdb

GPT-4 Strengthens Cybersecurity Defense with Formal Verification

By

@gdb

–

29 March 2023 2h48

GPT-4 for security, giving a real power boost for defenders. One encouraging (but still tentative) idea that I've heard over the years is that AI may permanently shift the favor to defenders; for example, by enabling formally verified systems.