Tag: chatgpt
-
Act fast to snuff out employee curiosity over ‘free’ AI apps
The word “free” has always tempted employees who are looking for an app or template to make their work easier. These days, combine “free” with “AI” and the lure is almost irresistible.Since the release of ChatGPT in late 2022, free AI-themed apps have exploded. Unfortunately, some are created by threat actors. One of the latest…
-
Faux ChatGPT, Claude API Packages Deliver JarkaStealer
Attackers are betting that the hype around generative AI (GenAI) is attracting less technical, less cautious developers who might be more inclined to download an open source Python code package for free access, without vetting it or thinking twice. First seen on darkreading.com Jump to article: www.darkreading.com/application-security/faux-chatgpt-claude-api-packages-jarkastealer
-
Code mit betrügerischer API kostet Programmierer 2500 US-Dollar
Ein Kryptowährungs-Interessierter wollte mit ChatGPT einen “Bump Bot” programmieren. Die KI hat eine betrügerische API in den Code eingebaut. First seen on heise.de Jump to article: www.heise.de/news/ChatGPT-Code-mit-betruegerischer-API-kostet-Programmierer-2500-US-Dollar-10169146.html
-
Cast a hex on ChatGPT to trick the AI into writing exploit code
First seen on theregister.com Jump to article: www.theregister.com/2024/10/29/chatgpt_hex_encoded_jailbreak/
-
Scam Crypto-API in Quellcode-Vorschlag schädigt Opfer um 2.500 US-Dollar
Heute noch eine unglaubliche Geschichte, die mir von einem Sicherheitsexperten zugespielt wurde. Jemand hat versucht, mittels ChatGPT Code für eine Anwendung erstellen zu lassen, die auch Kryptogelder transferieren können soll. Dabei wurde Schadcode eingebaut, der dafür sorgte, dass das Opfer … First seen on borncity.com Jump to article: www.borncity.com/blog/2024/11/24/chatgpt-wenn-bei-der-code-entwicklung-schadcode-injiziert-wird/
-
Fake ChatGPT, Claude PyPI packages spread JarkaStealer malware
First seen on scworld.com Jump to article: www.scworld.com/news/fake-chatgpt-claude-pypi-packages-spread-jarkastealer-malware
-
Prompt Injecting Your Way To Shell: OpenAI’s Containerized ChatGPT Environment
First seen on thesecurityblogger.com Jump to article: www.thesecurityblogger.com/prompt-injecting-your-way-to-shell-openais-containerized-chatgpt-environment/
-
PyPI Attack: ChatGPT, Claude Impersonators Deliver JarkaStealer via Python Libraries
Cybersecurity researchers have discovered two malicious packages uploaded to the Python Package Index (PyPI) repository that impersonated popular artificial intelligence (AI) models like OpenAI ChatGPT and Anthropic Claude to deliver an information stealer called JarkaStealer.The packages, named gptplus and claudeai-eng, were uploaded by a user named “Xeroline” in November 2023, attracting First seen on thehackernews.com…
-
Two PyPi Malicious Package Mimic ChatGPT Claude Steals Developers Data
Two malicious Python packages masquerading as tools for interacting with popular AI models ChatGPT and Claude were recently discovered on the Python Package Index (PyPI), the official repository for Python libraries. These packages reportedly remained undetected for over a year, silently compromising developer environments and exfiltrating sensitive data. As reported by a cybersecurity researcher, Leonid…
-
Mozilla 0Din Warns of ChatGPT Sandbox Flaws Enabling Python Execution
Mozilla’s 0Din uncovers critical flaws in ChatGPT’s sandbox, allowing Python code execution and access to internal configurations. OpenAI… First seen on hackread.com Jump to article: hackread.com/mozilla-0din-chatgpt-sandbox-flaws-python-execution/
-
ChatGPT Sandbox Flaws Allow Python Script Execution, File Manipulation
Mozilla’s 0Din uncovers critical flaws in ChatGPT’s sandbox, allowing Python code execution and access to internal configurations. OpenAI… First seen on hackread.com Jump to article: hackread.com/chatgpt-sandbox-flaws-python-script-file-manipulation/
-
ChatGPT Exposes Its Instructions, Knowledge & OS Files
According to Mozilla, users have a lot more power to manipulate ChatGPT than they might realize. OpenAI hopes those manipulations remain within a clearly delineated sandbox. First seen on darkreading.com Jump to article: www.darkreading.com/cloud-security/chatgpt-exposes-instructions-knowledge-os-files
-
ChatGPT allows access to underlying sandbox OS, “playbook” data
OpenAI’s containerized ChatGPT environment is open to limited yet extensive access to core instructions while allowing arbitrary file uploads and command execution within the isolated sandbox. First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/artificial-intelligence/chatgpt-allows-access-to-underlying-sandbox-os-playbook-data/
-
OpenAI details how threat actors are abusing ChatGPT
While threat actors are using generative AI tools like ChatGPT to run election influence operations and develop malware, OpenAI says the efforts are r… First seen on techtarget.com Jump to article: www.techtarget.com/searchsecurity/news/366613512/OpenAI-details-how-threat-actors-are-abusing-ChatGPT
-
KI-Jailbreak: ChatGPT mit Hex-Codes ausgetrickst
First seen on golem.de Jump to article: www.golem.de/news/ki-jailbreak-chatgpt-mit-hex-codes-ausgetrickst-2410-190310.html
-
Widespread ChatGPT credential compromise sought by OpenAI spoofing campaign
First seen on scworld.com Jump to article: www.scworld.com/brief/widespread-chatgpt-credential-compromise-sought-by-openai-spoofing-campaign
-
ChatGPT-4o can be used for autonomous voice-based scams
Researchers have shown that it’s possible to abuse OpenAI’s real-time voice API for ChatGPT-4o, an advanced LLM chatbot, to conduct financial scams wi… First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/security/chatgpt-4o-can-be-used-for-autonomous-voice-based-scams/
-
Businesses Worldwide Targeted in Large-Scale ChatGPT Phishing Campaign
Barracuda has observed a large-scale OpenAI impersonation campaign whose goal is to phish for ChatGPT credentials. The post Businesses Worldwide Targe… First seen on securityweek.com Jump to article: www.securityweek.com/businesses-worldwide-targeted-in-large-scale-chatgpt-phishing-campaign/
-
Mozilla: ChatGPT Can Be Manipulated Using Hex Code
LLMs tend to miss the forest for the trees, understanding specific instructions but not their broader context. Bad actors can take advantage of this m… First seen on darkreading.com Jump to article: www.darkreading.com/application-security/chatgpt-manipulated-hex-code
-
Bypassing ChatGPT Safety Guardrails, One Emoji at a Time
Tags: chatgptMozilla Researcher Uses Non-Natural Language to Jailbreak GPT-4o. Anyone can jailbreak GPT-4o’s security guardrails with hexadecimal encoding and emoj… First seen on govinfosecurity.com Jump to article: www.govinfosecurity.com/bypassing-chatgpt-safety-guardrails-one-emoji-at-time-a-26719
-
OpenAI’s new ChatGPT Search Chrome extension feels like a search hijacker
OpenAI’s new ChatGPT search Chrome extension feels like nothing more than a typical search hijacker, changing Chrome’s settings so your address bar se… First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/security/openais-new-chatgpt-search-chrome-extension-feels-like-a-search-hijacker/
-
ChatGPT Jailbreak: Researchers Bypass AI Safeguards Using Hexadecimal Encoding and Emojis
New jailbreak technique tricked ChatGPT into generating Python exploits and a malicious SQL injection tool. The post ChatGPT Jailbreak: Researchers By… First seen on securityweek.com Jump to article: www.securityweek.com/first-chatgpt-jailbreak-disclosed-via-mozillas-new-ai-bug-bounty-program/
-
New ChatGPT-4o Jailbreak Technique Enabling to Write Exploit Codes
Researcher Marco Figueroa has uncovered a method to bypass the built-in safeguards of ChatGPT-4o and similar AI models, enabling them to generate expl… First seen on gbhackers.com Jump to article: gbhackers.com/new-chatgpt-4o-jailbreak-technique/
-
How to jailbreak ChatGPT and trick the AI into writing exploit code using hex encoding
First seen on theregister.com Jump to article: www.theregister.com/2024/10/29/chatgpt_hex_encoded_jailbreak/
-
Can Security Experts Leverage Generative AI Without Prompt Engineering Skills?
A study at Rensselaer Polytechnic Institute presented at ISC2 Security Congress compared ChatGPT-written training prompted by security experts and pro… First seen on techrepublic.com Jump to article: www.techrepublic.com/article/generative-ai-security-training/
-
Gut gegen Böse dieser Zwiespalt der KI wird uns in naher Zukunft mehr und mehr beschäftigen
‘Alles steht im Zeichen der KI. Mittlerweile ist die künstliche Intelligenz nicht nur via ChatGPT, Sora und Midjourney für die breite Masse zugänglich… First seen on netzpalaver.de Jump to article: netzpalaver.de/2024/10/07/gut-gegen-boese-dieser-zwiespalt-der-ki-wird-uns-in-naher-zukunft-mehr-und-mehr-beschaeftigen/
-
Dane Stuckey Joins OpenAI as CISO
Former Palantir CISO joins ChatGPT maker OpenAI to lead cybersecurity efforts. The post Dane Stuckey Joins OpenAI as CISO appeared first on SecurityWe… First seen on securityweek.com Jump to article: www.securityweek.com/dane-stuckey-joins-openai-as-ciso/
-
OpenAI bestätigt Nutzung von ChatGPT zur Malware-Entwicklung
First seen on heise.de Jump to article: www.heise.de/news/OpenAI-gibt-zu-ChatGPT-wird-zur-Malware-Entwicklung-genutzt-9979470.html
-
OpenAI confirms threat actors use ChatGPT to write malware
OpenAI has disrupted over 20 malicious cyber operations abusing its AI-powered chatbot, ChatGPT, for debugging and developing malware, spreading misin… First seen on bleepingcomputer.com Jump to article: www.bleepingcomputer.com/news/security/openai-confirms-threat-actors-use-chatgpt-to-write-malware/