ChatGPT side-channel attack has easy fix: token obfuscation The Register

In brief Almost as quickly as a paper came out last week revealing an AI side-channel vulnerability, Cloudflare researchers have figured out how to solve it: just obscure your token size.
The paper [PDF], from researchers at the Offensive AI Institute at Israel's Ben Gurion University, found an issue with how all non-Google ChatGPT derivatives transmit chat sessions between LLM servers and users.
When operating in streaming mode, ChatGPT and related AIs send tokens sequentially - meaning the response from the AI flows bit-by-bit to the user instead of all at once after the bot has decided how to answer.
A malicious actor in the middle with the ability to intercept network traffic could sniff those LLM tokens.
You may be thinking that those response tokens are encrypted, and you'd be right.
Here's where the Ben Gurion researchers got crafty: they built their own specially trained LLMs designed to examine the packets and understand what they mean, with a decent degree of accuracy.
Cloudflare, offers its own ChatGPT-based AIs in the form of products like Workers AI and AI Gateway, seems to have figured out how to address the issue with relative ease by padding its tokens.
Another Patch Tuesday, another quiet week on the vulnerability front - at least from the major vendors, whose issues were already highlighted on The Register.
A few operational tech vulnerabilities emerged and, as has been established, that's where the big threats lie nowadays.
CVSS 10.0 - Multiple CVEs: Siemens Cerberus and Sinteso fire protection systems contain a number of issues, including a rather serious classic buffer overflow vulnerability, that could allow access to fire protection system networks.
CVSS 9.8 - Multiple CVEs: A number of Mitsubishi Electric MELSEC-Q/L series controllers contain incorrect pointer scaling and integer overflow/wraparound issues that could allow an attacker to read arbitrary info or perform RCE. CVSS 9.8 - Multiple CVEs: Siemens RUGGEDCOM APE1808 devices, which use Fortinet, are suffering from a bunch of issues linked to problems with FortiOS, FortiProxy and other well-perforated products.
CVSS 9.8 - Too many CVEs: Siemens SIMATIC RF160B RFID readers versions prior to 2.2 contain 157 CVEs that let an attacker execute arbitrary code with privileged access.
CVSS 9.8 - Multiple CVEs: Siemens SINEMA remote connect server is vulnerable to XSS and is improperly controlling access.
CVSS 8.8 - Multiple CVEs: Delta Electronics DIAEnergie software prior to v1.10.00.005 contains several SQL injection vulnerabilities and other issues that could let an attacker escalate privileges, disclose information or disrupt systems.
CVSS 8.7 - Multiple CVEs: More vulns in Siemens RUGGEDCOM APE1808, again due to the inclusion of Fortinet, this time with problems in Fortinet Next-Gen Firewall that could lead to DoS and RCE with elevated permissions.
Infostealer malware is everywhere nowadays, and a new campaign is trying to lure Roblox users into downloading one disguised as a tool to optimize frames-per-second performance on the platform.
Once installed, the malicious app uses Powershell commands to install the malware, which is able to exfiltrate location data, Wi-Fi network information, passwords, Roblox user data and even in-game currency details.
With the majority of Roblox users being children, parents should be aware of the threat posed by such malware - especially if kids are playing around on a machine also used for business.
Jonathan Katz, a former manager at an unnamed telecom store in New Jersey, pled guilty this week to conspiring to gain unauthorized access to a protected computer by performing SIM swaps for someone else.
According to the US Department of Justice, while manager of the store Katz used his access to company computers to swap customer SIM numbers, giving account access to an unnamed co-conspirator who was able to access the victims' email, social media and cryptocurrency accounts.


This Cyber News was published on go.theregister.com. Publication date: Mon, 18 Mar 2024 03:13:08 +0000


Cyber News related to ChatGPT side-channel attack has easy fix: token obfuscation The Register

Vulnerability Summary for the Week of January 29, 2024 - Es PrimaryVendor - Product cups easy - cups easy Description A vulnerability has been reported in Cups Easy, version 1.0, whereby user-controlled inputs are not sufficiently encoded, resulting in a Cross-Site Scripting vulnerability via ...
4 months ago Cisa.gov
Vulnerability Summary for the Week of January 22, 2024 - Es PrimaryVendor - Product ajaysharma - cups easy Description A vulnerability has been reported in Cups Easy, version 1.0, whereby user-controlled inputs are not sufficiently encoded, resulting in a Cross-Site Scripting vulnerability via ...
5 months ago Cisa.gov
XSS Marks the Spot: Digging Up Vulnerabilities in ChatGPT - With its widespread use among businesses and individual users, ChatGPT is a prime target for attackers looking to access sensitive information. In this blog post, I'll walk you through my discovery of two cross-site scripting vulnerabilities in ...
4 months ago Imperva.com
How enterprises are using gen AI to protect against ChatGPT leaks - ChatGPT is the new DNA of shadow IT, exposing organizations to new risks no one anticipated. Enterprise workers are gaining a 40% performance boost thanks to ChatGPT based on a recent Harvard University study. A second study from MIT discovered that ...
5 months ago Venturebeat.com
How Are Security Professionals Managing the Good, The Bad and The Ugly of ChatGPT? - ChatGPT has emerged as a shining light in this regard. Already we're seeing the platform being integrated into corporate systems, supporting in areas such as customer success or technical support. The bad: The risks surrounding ChatGPT. Of course, ...
6 months ago Cyberdefensemagazine.com
ChatGPT Extensions Could be Exploited to Steal Data and Sensitive Information - API security professionals Salt Security have released new threat research from Salt Labs highlighting critical security flaws within ChatGPT plugins, presenting a new risk for enterprises. Plugins provide AI chatbots like ChatGPT access and ...
3 months ago Itsecurityguru.org
Google to Announce Chat-GPT Rival On February 8 Event - There seems to be a lot of consternation on Google's part at the prospect of a showdown with ChatGPT on the February 8 event. The search giant has been making moves that suggest it is preparing to enter the market for large language models, where ...
1 year ago Cybersecuritynews.com
Google Researchers' Attack Prompts ChatGPT to Reveal Its Training Data - A team of researchers primarily from Google's DeepMind systematically convinced ChatGPT to reveal snippets of the data it was trained on using a new type of attack prompt which asked a production model of the chatbot to repeat specific words forever. ...
7 months ago 404media.co
Researchers Uncover Simple Technique to Extract ChatGPT Training Data - Can getting ChatGPT to repeat the same word over and over again cause it to regurgitate large amounts of its training data, including personally identifiable information and other data scraped from the Web? The answer is an emphatic yes, according to ...
7 months ago Darkreading.com
ChatGPT Clone Apps Collecting Personal Data on iOS, Play Store - On Android devices, one of the apps analyzed by researchers has more than 100,000 downloads, tracks, and shares location data with ByteDance and Amazon, etc. ChatGPT, the AI software, has already taken the Internet by storm, and that is why ...
1 year ago Hackread.com
Are you sure you want to share that with ChatGPT? How Metomic helps stop data leaks - Open AI's ChatGPT is one of the most powerful tools to come along in a lifetime, set to revolutionize the way many of us work. Workers aren't content to wait until organizations work this question out, however: Many are already using ChatGPT and ...
4 months ago Venturebeat.com
From Implicit to Authorization Code With PKCE, BFF - Lack of Refresh Token Support occurs when there are no refresh tokens, and frequent requests for new tokens are necessary, increasing the chances of token leakage and misuse. The Implicit Flow had several security vulnerabilities, such as token ...
3 days ago Feeds.dzone.com
ChatGPT side-channel attack has easy fix: token obfuscation The Register - In brief Almost as quickly as a paper came out last week revealing an AI side-channel vulnerability, Cloudflare researchers have figured out how to solve it: just obscure your token size. The paper [PDF], from researchers at the Offensive AI ...
3 months ago Go.theregister.com
Crypto Deception Unveiled: Check Point Research Reports Manipulation of Pool Liquidity Skyrockets Token Price by 22,000% - Deceptive actors are manipulating pool liquidity, sending token prices soaring by a shocking 22,000%. 80,000 Heist Unveiled: The manipulation of pool liquidity resulted in a swift and calculated theft of $80,000 from unsuspecting token holders. Check ...
6 months ago Blog.checkpoint.com
OpenAI rolls out imperfect fix for ChatGPT data leak flaw - OpenAI has mitigated a data exfiltration bug in ChatGPT that could potentially leak conversation details to an external URL. According to the researcher who discovered the flaw, the mitigation isn't perfect, so attackers can still exploit it under ...
6 months ago Bleepingcomputer.com
Locking Down ChatGPT: A User's Guide to Strengthening Account Security - OpenAI officials said that the user who reported his ChatGPT history was a victim of a compromised ChatGPT account, which resulted in the unauthorized logins. OpenAI has confirmed that the unauthorized logins originate from Sri Lanka, according to an ...
5 months ago Cysecurity.news
Foreign states already using ChatGPT maliciously, UK IT leaders believe - Most UK IT leaders believe that foreign states are already using the ChatGPT chatbot for malicious purposes against other nations. That's according to a new study from BlackBerry, which surveyed 500 UK IT decision makers revealing that, while 60% of ...
1 year ago Csoonline.com
CRN Recognizes three Check Point Channel Stars in its 2024 Women of the Channel list - CRN has recognized Check Point's Head of Americas Channel Sales, Nisha Holt, for her outstanding achievements as one of the Women of the Channel Power 100. Rebecca James and Lauren Ventura have also earned a spot on the esteemed Women of the Channel ...
1 month ago Blog.checkpoint.com
CVE-2013-0135 - Multiple SQL injection vulnerabilities in PHP Address Book 8.2.5 allow remote attackers to execute arbitrary SQL commands via the id parameter to (1) addressbook/register/delete_user.php, (2) addressbook/register/edit_user.php, or (3) ...
6 years ago
Google Researchers Find ChatGPT Queries Collect Personal Data - The LLMs are evolving rapidly with continuous advancements in their research and applications. Recently, cybersecurity researchers at Google discovered how threat actors can exploit ChatGPT queries to collect personal data. StorageGuard scans, ...
7 months ago Cybersecuritynews.com
One Year of ChatGPT: Domains Evolved by Generative AI - ChatGPT has recently completed one year after its official launch. Since it introduced the world to the future, by showing what a human-AI interaction looks like, ChatGPT has eventually transformed the entire tech realm into a cultural phenomenon. ...
6 months ago Cysecurity.news
CVE-2017-8367 - Buffer overflow in Ether Software Easy MOV Converter 1.4.24, Easy DVD Creator, Easy MPEG/AVI/DIVX/WMV/RM to DVD, Easy Avi/Divx/Xvid to DVD Burner, Easy MPEG to DVD Burner, Easy WMV/ASF/ASX to DVD Burner, Easy RM RMVB to DVD Burner, Easy CD DVD Copy, ...
7 years ago
Hangzhou's Cybersecurity Breakthrough: How ChatGPT Elevated Ransomware Resolution - The Chinese media reported on Thursday that local police have arrested a criminal gang from Hangzhou who are using ChatGPT for program optimization to carry out ransomware attacks for the purpose of extortion. An organization in the Shangcheng ...
6 months ago Cysecurity.news
CVE-2017-17713 - Trape before 2017-11-05 has SQL injection via the /nr red parameter, the /nr vId parameter, the /register User-Agent HTTP header, the /register country parameter, the /register countryCode parameter, the /register cpu parameter, the /register isp ...
6 years ago
CVE-2017-17714 - Trape before 2017-11-05 has XSS via the /nr red parameter, the /nr vId parameter, the /register User-Agent HTTP header, the /register country parameter, the /register countryCode parameter, the /register cpu parameter, the /register isp parameter, ...
6 years ago

Latest Cyber News


Cyber Trends (last 7 days)


Trending Cyber News (last 7 days)