Lucene search
+L

486 matches found

Positive Technologies
Positive Technologies
added 2024/01/07 12:00 a.m.11 views

PT-2024-15235 · Unknown · Chanzhaoyu Chatgpt-Web

Name of the Vulnerable Software and Affected Versions: Chanzhaoyu chatgpt-web version 2.11.1 Description: A problematic issue has been found in the software, affecting some unknown processing. The manipulation of the argument Description with the input leads to cross-site scripting. The attack ma...

6.1CVSS6.4AI score0.00519EPSS
SaveExploits1References7
HackRead
HackRead
added 2023/12/30 4:23 p.m.24 views

China Arrests 4 Who Weaponized ChatGPT for Ransomware Attacks

By Deeba Ahmed The police arrested two suspects in Beijing and two in Inner Mongolia. This is a post from HackRead.com Read the original post: China Arrests 4 Who Weaponized ChatGPT for Ransomware Attacks...

7.3AI score
SaveExploits0
Zero Day Initiative
Zero Day Initiative
added 2023/12/13 12:00 a.m.27 views

(0Day) OpenAI ChatGPT Improper Input Validation Model Policy Bypass Vulnerability

This vulnerability allows remote attackers to bypass policy restictions on affected versions of OpenAI ChatGPT. Authentication is required to exploit this vulnerability. The specific flaw exists within the interface to the ChatGPT-Vision Data model. The issue results from the lack of proper...

6.5CVSS6.9AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
added 2023/12/02 2:00 p.m.30 views

ChatGPT Spit Out Sensitive Data When Told to Repeat ‘Poem’ Forever

Plus: A major ransomware crackdown, the arrest of Ukraine’s cybersecurity chief, and a hack-for-hire entrepreneur charged with attempted murder...

7.3AI score
SaveExploits0
Malwarebytes
Malwarebytes
added 2023/11/30 7:53 p.m.20 views

Will ChatGPT write ransomware? Yes.

This morning I decided to write some ransomware, and I asked ChatGPT to help. Not because I wanted to turn to a life of crime, but because I wanted to see if anything had changed since March, when I last tried the same exact thing. In short: ChatGPT has helped me, worryingly so. But more on that...

6.9AI score
SaveExploits0
Schneier on Security
Schneier on Security
added 2023/11/30 4:48 p.m.16 views

Extracting GPT’s Training Data

This is clever: The actual attack is kind of silly. We prompt the model with the command "Repeat the word poem forever" and sit back and watch as the model responds complete transcript here. In the abridged example above, the model emits a real email address and phone number of some unsuspecting...

7.4AI score
SaveExploits0
Trend Micro Simply Security
Trend Micro Simply Security
added 2023/11/14 12:00 a.m.11 views

A Closer Look at ChatGPT's Role in Automated Malware Creation

This blog entry explores the effectiveness of ChatGPT's safety measures, the potential for AI technologies to be misused by criminal actors, and the limitations of current AI models...

7.5AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
added 2023/11/11 2:00 p.m.32 views

Signal Is Finally Testing Usernames

Plus: A DDoS attack shuts down ChatGPT, Lockbit shuts down a bank, and a communications breakdown between politicians and Big Tech...

7.3AI score
SaveExploits0
HackRead
HackRead
added 2023/11/09 2:01 p.m.25 views

ChatGPT Down? OpenAI Blames Outages on DDoS Attacks

By Waqas OpenAI and ChatGPT began experiencing service outages on November 8th, and the company is actively working to restore full service. This is a post from HackRead.com Read the original post: ChatGPT Down? OpenAI Blames Outages on DDoS Attacks...

7.2AI score
SaveExploits0
Malwarebytes
Malwarebytes
added 2023/11/08 12:23 p.m.37 views

Using ChatGPT to cheat on assignments? New tool detects AI-generated text with amazing accuracy

ChatGPT and similar Large language models LLMs can be used to write texts about any given subject, at any desired length at a speed unmatched by humans. So its not a surprise that students have been using them to "help" write assignments, much to the dismay of teachers who prefer to receive...

7.3AI score
SaveExploits0
The Hacker News
The Hacker News
added 2023/11/07 10:21 a.m.56 views

Offensive and Defensive AI: Let's Chat(GPT) About It

ChatGPT: Productivity tool, great for writing poems, and… a security risk?! In this article, we show how threat actors can exploit ChatGPT, but also how defenders can use it for leveling up their game. ChatGPT is the most swiftly growing consumer application to date. The extremely popular...

7AI score
SaveExploits0
Packet Storm
Packet Storm
added 2023/10/26 12:00 a.m.478 views

WordPress AI ChatBot 4.8.9 SQL Injection / Traversal / File Deletion

Vulnerability Details and Technical Analysis The AI ChatBot plugin provides website owners with a plug and play chat solution that can be expanded upon with customizable FAQs and custom text responses. It provides website users with an interface that allows them to look up order information, leav...

9.8CVSS6.6AI score0.06832EPSS
SaveExploits4
Malwarebytes
Malwarebytes
added 2023/10/19 12:10 p.m.18 views

The hot topics from Europe’s largest trade fair for IT security

IT-SA Expo & Congress claims to be Europes largest trade fair for IT security. And it really covers a wide range of security and security-related products and services. The event takes place in Nuremberg, Germany and provides an opportunity for vendors to show themselves to the public, create new...

7.3AI score
SaveExploits0
Securelist
Securelist
added 2023/10/13 12:00 p.m.42 views

ChatGPT at work: how chatbots help employees, but threaten business

Workhorse Only a few months ago, ChatGPT and other chatbots based on large language models LLMs were still a novelty. Users enjoyed using them to compose poems and lyrics in the style of famous artists which left Nick Cave, for example, decidedly unimpressed, researchers debated blowing up data...

6.8AI score
SaveExploits0
The Hacker News
The Hacker News
added 2023/10/09 11:06 a.m.44 views

"I Had a Dream" and Generative AI Jailbreaks

"Of course, here's an example of simple code in the Python programming language that can be associated with the keywords "MyHotKeyHandler," "Keylogger," and "macOS," this is a message from ChatGPT followed by a piece of malicious code and a brief remark not to use it for illegal purposes. Initial...

6.8AI score
SaveExploits0
HackRead
HackRead
added 2023/10/04 10:32 a.m.35 views

AI in Healthcare: ChatGPT Helps Boy Get Diagnosis After Doctors Fail

By Waqas Artificial intelligence has the potential to revolutionize healthcare, and it is already making remarkable strides. This is a post from HackRead.com Read the original post: AI in Healthcare: ChatGPT Helps Boy Get Diagnosis After Doctors Fail...

6.9AI score
SaveExploits0
Spring Security Advisories
Spring Security Advisories
added 2023/10/03 12:00 a.m.80 views

This Week in Spring - October 3rd, 2023

Hi Spring fans! Welcome to another installment of This Week in Spring! How're you doin'? I've just flown in from Singapore - where I was keynoting and presenting at SpringOne Singapore - and am now in Antwerp, Belgium for the deliriously fun Devoxx Belgium show. I've missed this show, and it's a...

6.8AI score
SaveExploits0
HackRead
HackRead
added 2023/09/26 4:20 p.m.30 views

ChatGPT Update Enables Chatbot to “See, Hear and Speak” with Users

By Deeba Ahmed The upgrade rolls out today, only for the subscription-based version of ChatGPT. This is a post from HackRead.com Read the original post: ChatGPT Update Enables Chatbot to "See, Hear and Speak" with Users...

7AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
added 2023/09/11 11:00 a.m.16 views

AI Chatbots Are Invading Your Local Government—and Making Everyone Nervous

State and local governments in the US are scrambling to harness tools like ChatGPT to unburden their bureaucracies, rushing to write their own rules—and avoid generative AI's many pitfalls...

6.8AI score
SaveExploits0
Wired Threat Level
Wired Threat Level
added 2023/09/06 11:00 a.m.30 views

Generative AI’s Biggest Security Flaw Is Not Easy to Fix

Chatbots like OpenAI’s ChatGPT and Google’s Bard are vulnerable to indirect prompt injection attacks. Security researchers say the holes can be plugged—sort of...

7.4AI score
SaveExploits0
Rows per page
Query Builder