Artificial Intelligence
Different research teams have demonstrated jailbreaks against ChatGPT, DeepSeek, and Alibaba’s Qwen AI models.
Hi, what are you looking for?
SecurityWeek
All posts tagged "ChatGPT"
Email Security
Barracuda has observed a large-scale OpenAI impersonation campaign whose goal is to phish for ChatGPT credentials.
Artificial Intelligence
New jailbreak technique tricked ChatGPT into generating Python exploits and a malicious SQL injection tool.
Artificial Intelligence
OpenAI has disrupted 20 cyber and influence operations this year, including the activities of Iranian and Chinese state-sponsored hackers.
Artificial Intelligence
Mira Murati, who served a few days as its interim CEO during a period of turmoil last year, said she’s leaving the artificial intelligence...
Funding/M&A
SplxAI has raised $2 million in pre-seed funding to help organizations identify vulnerabilities in AI chat applications.
Artificial Intelligence
The tools are being positioned as crucial to help business customers meet requirements for regulations like FINRA, HIPAA, and GDPR.
Artificial Intelligence
Few people understand AI, nor how to use nor control it, nor where it is going. Yet politicians wish to regulate it.
Artificial Intelligence
ChatGPT maker OpenAI was breached in 2023, but the company says source code and customer data were not accessed.
Artificial Intelligence
Microsoft has tricked several gen-AI models into providing forbidden information using a jailbreak technique named Skeleton Key.
Artificial Intelligence
SecurityWeek editor-at-large Ryan Naraine examines the broad tension between tech innovation and privacy rights at a time when ChatGPT-like bots and generative-AI apps are...
Artificial Intelligence
OpenAI is setting up a new safety and security committee and has begun training a new artificial intelligence model to supplant the GPT-4 system...
Artificial Intelligence
When not scamming other criminals, criminals are concentrating on the use of mainstream AI products rather than developing their own AI systems.
Artificial Intelligence
Software developers relying on AI chatbots for building applications may end up using hallucinated software packages.
Artificial Intelligence
Artificial intelligence computing giant NVIDIA patches flaws in ChatRTX for Windows and warns of code execution and data tampering risks.
Artificial Intelligence
Three types of vulnerabilities related to ChatGPT plugins could have led to data exposure and account takeovers.
Artificial Intelligence
Microsoft threat hunters say foreign APTs are interacting with OpenAI’s ChatGPT to automate malicious vulnerability research, target reconnaissance and malware creation tasks.
Artificial Intelligence
Prompt Security emerges from stealth with $5 million in seed to help businesses with generative-AI security tasks.
Artificial Intelligence
SecurityWeek interviews a wide spectrum of security experts on AI-driven cybersecurity use-cases that are worth immediate attention.
Artificial Intelligence
A researcher has shown how malicious actors can create custom GPTs that can phish for credentials and exfiltrate them to external servers.
Artificial Intelligence
An unreleased OpenAI cyber model found and exploited 948 distinct Linux kernel privilege escalation bugs for about $1.2 million.
Artificial Intelligence
Artificial Intelligence
Malware & Threats
Phishing
More than 200 sites were seen serving phishing content to first-time visitors but not to those who revisit.
Vulnerabilities
Artificial Intelligence
