Lucene search
+L

481 matches found

Malwarebytes
Malwarebytes
added 2023/06/05 10:0 a.m.22 views

Trusting AI not to lie: The cost of truth: Lock and Code S04E12

In May, a lawyer who was defending their client in a lawsuit against Columbia's biggest airline, Avianca, submitted a legal filing before a court in Manhattan, New York, that listed several previous cases as support for their main argument to continue the lawsuit. But when the court reviewed the...

6.9AI score
SaveExploits0
OSV
OSV
added 2023/05/31 6:3 p.m.24 views

CVE-2023-33979 gpt_academic's Configuration File vulnerable to File Information Disclosure

gptacademic provides a graphical interface for ChatGPT/GLM. A vulnerability was found in gptacademic 3.37 and prior. This issue affects some unknown processing of the component Configuration File Handler. The manipulation of the argument file leads to information disclosure. Since no sensitive...

6.5CVSS6.1AI score0.00733EPSS
SaveExploits0References4
CVE
CVE
added 2023/05/31 6:3 p.m.53 views

CVE-2023-33979

The CVE-2023-33979 issue affects gpt_academic (3.37 and earlier), where improper handling of the Configuration File Handler allows manipulation of the file argument resulting in information disclosure. Read access via the /file route can leak sensitive information from working directories, partic...

6.5CVSS6.4AI score0.00733EPSS
SaveExploits0References2Affected Software1
The Hacker News
The Hacker News
added 2023/05/31 8:30 a.m.4 views

RomCom RAT Using Deceptive Web of Rogue Software Sites for Covert Attacks

The threat actors behind RomCom RAT are leveraging a network of fake websites advertising rogue versions of popular software at least since July 2022 to infiltrate targets. Cybersecurity firm Trend Micro is tracking the activity cluster under the name Void Rabisu, which is also known as Tropical...

7.1AI score
SaveExploits0
The Hacker News
The Hacker News
added 2023/05/30 7:2 a.m.5 views

Sneaky DogeRAT Trojan Poses as Popular Apps, Targets Indian Android Users

A new open source remote access trojan RAT called DogeRAT targets Android users primarily located in India as part of a sophisticated malware campaign. The malware is distributed via social media and messaging platforms under the guise of legitimate applications like Opera Mini, OpenAI ChatGPT, a...

6.8AI score
SaveExploits0
Kitploit
Kitploit
added 2023/05/29 12:30 p.m.114 views

PentestGPT - A GPT-empowered Penetration Testing Tool

A GPT-empowered penetration testing tool. Common Questions Q : What is PentestGPT? A : PentestGPT is a penetration testing tool empowered by ChatGPT. It is designed to automate the penetration testing process. It is built on top of ChatGPT and operate in an interactive mode to guide penetration...

7.3AI score
SaveExploits0References4
Schneier on Security
Schneier on Security
added 2023/05/25 11:5 a.m.14 views

On the Poisoning of LLMs

Interesting essay on the poisoning of LLMs--ChatGPT in particular: Given that weve known about model poisoning for years, and given the strong incentives the black-hat SEO crowd has to manipulate results, its entirely possible that bad actors have been poisoning ChatGPT for months. We dont know...

7AI score
SaveExploits0
Patchstack
Patchstack
added 2023/05/19 12:0 a.m.11 views

WordPress AI Engine: ChatGPT Chatbot Plugin <= 1.6.82 is vulnerable to Cross Site Scripting (XSS)

Software AI Engine: ChatGPT Chatbot Type Plugin Vulnerable versions = 1.6.82 Fixed in 1.6.83 OWASP Top 10 A7: Cross-Site Scripting XSS Classification Cross Site Scripting XSS CVE CVE-2023-2580 Patch priority Low CVSS severity Low 5.9 Developer Claim ownership PSID 262a43aa67fb Credits Felipe...

4.8CVSS5.8AI score0.0047EPSS
SaveExploits2References4Affected Software1
Wired Threat Level
Wired Threat Level
added 2023/05/17 10:0 a.m.18 views

ChatGPT Scams Are Infiltrating Apple's App Store and Google Play

An explosion of interest in OpenAI’s sophisticated chatbot means a proliferation of “fleeceware” apps that trick users with sneaky in-app subscriptions...

6.9AI score
SaveExploits0
Trend Micro Simply Security
Trend Micro Simply Security
added 2023/05/17 12:0 a.m.20 views

Security Vulnerabilities of ChatGPT-Generated Code

Discover the cybersecurity risks of AI-generated code, learn how to protect your applications, and understand how the rise of ChatGPT is impacting software development...

7AI score
SaveExploits0
Wallarm Lab
Wallarm Lab
added 2023/05/16 1:58 p.m.71 views

ChatGPT: Friend or Foe? | API Security Newsletter

Welcome to our April API newsletter, recapping some of the events of last month. This month’s topic is Generative AI tools e.g., ChatGPT in cybersecurity. It – along with API Security – dominated the 2023 RSA Conference, and there’s plenty of digital ink being spilled on the topic. Be sure to wat...

7.5CVSS8.8AI score0.35604EPSS
SaveExploits14
Trend Micro Simply Security
Trend Micro Simply Security
added 2023/05/12 12:0 a.m.19 views

Malicious AI Tool Ads Used to Deliver Redline Stealer

We’ve been observing malicious advertisement campaigns in Google’s search engine with themes that are related to AI tools such as Midjourney and ChatGPT...

7AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
added 2023/05/09 6:0 a.m.21 views

How To Delete Your Data From ChatGPT

OpenAI has new tools that give you more control over your information—although they may not go far enough...

7AI score
SaveExploits0
Trend Micro Simply Security
Trend Micro Simply Security
added 2023/05/09 12:0 a.m.12 views

How to Build a Simple Application Powered by ChatGPT

OpenAI’s ChatGPT API enables applications to access and integrate ChatGPT, a large language model LLM that generates human-like responses to input. Learn how to build a web application that utilizes ChatGPT to generate useful output...

7AI score
SaveExploits0
HackRead
HackRead
added 2023/05/08 11:29 p.m.12 views

ChatGPT Can Vastly Improve Healthcare, But The Industry Needs A Secure Database First

By Waqas ChatGPT’s capabilities have been put to the test in numerous ways, and it has successfully passed no less than four U.S. benchmarking examinations for physicians. This is a post from HackRead.com Read the original post: ChatGPT Can Vastly Improve Healthcare, But The Industry Needs A Secu...

7AI score
SaveExploits0
Malwarebytes
Malwarebytes
added 2023/05/08 2:0 a.m.31 views

A week in security (May 1 - 7)

Last week on Malwarebytes Labs: How to protect your small business from social engineering Microsoft: You're already using the last version of Windows 10 Is it OK to train an AI on your images, without permission? Upcoming webinar: Is EDR or MDR better for your business? Google Authenticator WILL...

6.9AI score
SaveExploits0
The Hacker News
The Hacker News
added 2023/05/04 8:57 a.m.5 views

Meta Takes Down Malware Campaign That Used ChatGPT as a Lure to Steal Accounts

Meta said it took steps to take down more than 1,000 malicious URLs from being shared across its services that were found to leverage OpenAI's ChatGPT as a lure to propagate about 10 malware families since March 2023. The development comes against the backdrop of fake ChatGPT web browser extensio...

7.1AI score
SaveExploits0
The Hacker News
The Hacker News
added 2023/05/04 8:57 a.m.41 views

Meta Takes Down Malware Campaign That Used ChatGPT as a Lure to Steal Accounts

Meta said it took steps to take down more than 1,000 malicious URLs from being shared across its services that were found to leverage OpenAI's ChatGPT as a lure to propagate about 10 malware families since March 2023. The development comes against the backdrop of fake ChatGPT web browser extensio...

7.1AI score
SaveExploits0
Malwarebytes
Malwarebytes
added 2023/05/03 6:45 p.m.24 views

How to keep your ChatGPT conversations out of its training data

Last week, OpenAI announced it had given ChatGPT users the option to turn off their chat history. ChatGPT is a "generative AI", a machine learning algorithm that can understand language and generate written responses. Users can interact with it by asking questions, and the conversations users hav...

6.4AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
added 2023/05/03 12:0 p.m.21 views

Meta Moves to Counter New Malware and Repeat Account Takeovers

The company is adding new tools as bad actors use ChatGPT-themed lures and mask their infrastructure in an attempt to trick victims and elude defenders...

6.8AI score
SaveExploits0
Rows per page
Query Builder