Subj : More security flaws found in popular AI chatbots  and they could
To   : All
From : TechnologyDaily
Date : Fri Mar 15 2024 17:30:06

More security flaws found in popular AI chatbots  and they could mean hackers 
can learn all your secrets

Date:
Fri, 15 Mar 2024 17:16:16 +0000

Description:
A lot can be picked up by listening to the traffic, but researchers have a 
solution.

FULL STORY
======================================================================

If a hacker can monitor the internet traffic between their target and the 
targets cloud-based AI assistant, they could easily pick up on the 
conversation. And if that conversation contained sensitive information - that 
information would end up in the attackers hands, as well. 

This is according to a new analysis from researchers at the Offensive AI 
Research Lab from Ben-Gurion University in Israel, who found a way to deploy 
side channel attacks on targets using all Large Language Model (LLM) 
assistants, save for Google Gemini. 

That includes OpenAIs powerhouse, Chat-GPT. The "padding" technique 

Currently, anybody can read private chats sent from ChatGPT and other 
services, Yisroel Mirsky, head of the Offensive AI Research Lab told 
ArsTechnica . 

This includes malicious actors on the same Wi-Fi or LAN as a client (e.g., 
same coffee shop), or even a malicious actor on the Internetanyone who can 
observe the traffic. The attack is passive and can happen without OpenAI or 
their client's knowledge. OpenAI encrypts their traffic to prevent these 
kinds of eavesdropping attacks, but our research shows that the way OpenAI is 
using encryption is flawed, and thus the content of the messages are exposed. 

Basically, in a bid to make the tool as fast as possible - the developers 
opened the doors to crooks picking up on the contents. When the chatbot 
starts sending back its response, it doesnt send it all at once. It sends 
small snippets, in the form of tokens, to speed the process up. These tokens 
may be encrypted, but as theyre being sent one by one, as soon as theyre 
generated, that allows the attackers to analyze them. 

The researchers analyzed the tokens size, length, the sequence through which 
they arrive, and more. The analysis, and subsequent refinement, resulted in 
decrypted responses which were almost identical to the ones seen by the 
victim. 

The researchers suggested developers do one of two things: either stop 
sending tokens one at the time, or fix all of them to the length of the 
largest possible packet, making analysis impossible. This technique, which 
they dubbed padding, was adopted by OpenAI and Cloudflare. More from 
TechRadar Pro LockBit ransomware still poses a major threat  ScreenConnect 
under attack from new malware Here's a list of the best firewalls around 
today These are the best endpoint security tools right now



======================================================================
Link to news story:
https://www.techradar.com/pro/security/more-security-flaws-found-in-popular-ai
-chatbots-and-they-could-mean-hackers-can-learn-all-your-secrets


--- Mystic BBS v1.12 A47 (Linux/64)
 * Origin: tqwNet Technology News (1337:1/100)

.