Author: Ng Chong
-
Strings of Nonsense Convince AI Chatbots to Abandon Ethical Rules
⋅
Continuing previous coverage of development in AI systems, I wanted to share a study and demo from Carnegie Mellon University in Pittsburgh, Pennsylvania and the Center for AI Safety in San Francisco, California revealing a new spin on how chatbot safeguards are susceptible to attacks. AI chatbots like OpenAI’s ChatGPT, Google’s Bard, and Anthropic’s Claude don’t have…
-
Privacy bug in Windows 11’s snipping tool
⋅
Windows 11 built-in snipping tool allows users to take screenshots and perform basic image editing tasks, such as cropping, annotating, and highlighting. It also includes a redaction feature that enables users to remove sensitive information from an image before saving or sharing it. Despite being a useful tool, it has a vulnerability that could have…
-
AI Image Generators Replicate Training Data, Pose Privacy Concerns
⋅
If you’ve been following the news, you’ve heard AI image generators have captured the public imagination. While concerns about “digital forgery” and copyright infringement have gotten much attention given the technology’s ability to mimic artist styles and subjects, concerns about privacy are also being raised. Training images are pulled from publicly available internet sources regardless…
-
MFA is good, but not good enough
⋅
Hackers attempt to log in to our online accounts daily by the hundreds. The extra protection layer provided by MFA to the sign-in process dramatically reduces the number of successful attacks. While we are relieved that MFA is doing a good job of keeping our online accounts safe, we need to continue to advise our…