More results...
Researchers from Carnegie Mellon University and the Center for A.I. Safety have discovered a new prompt injection method to override the guardrails of large language models (LLMs). These guardrails are safety measures designed to prevent AI fr…
The forum’s goal is to establish “guardrails” to mitigate the risk of AI. Learn about the group’s four core objectives, as well as the criteria for membership.
Security experts from HackerOne and beyond weigh in on malicious prompt engineering and other attacks that could strike through LLMs.
Interesting research: “(Ab)using Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs“:
Abstract: We demonstrate how images and sounds can be used for indirect prompt and instruction injection in multi-modal LLMs. An attacker generates an adversarial perturbation corresponding to the prompt and blends it into an image or audio recording. When the user asks the (unmodified, benign) model about the perturbed image or audio, the perturbation steers the model to output the attacker-chosen text and/or make the subsequent dialog follow the attacker’s instruction. We illustrate this attack with several proof-of-concept examples targeting LLaVa and PandaGPT…
For every 10,000 enterprise users, an enterprise organization is experiencing approximately 183 incidents of sensitive data being posted to ChatGPT per month, according to Netskope. Source code accounts for the largest share of sensitive data being exp…
By Christina A. Cassidy in Charleston CHARLESTON, S.C. (AP)…
Fraudsters are spreading scams on Facebook that pose as ads for legitimate AI tools, according to researchers at Check Point. The Facebook pages impersonate ChatGPT, Google Bard, Midjourney, Jasper, and more.
Fraudsters are spreading scams on Facebook that pose as ads for legitimate AI tools, according to researchers at Check Point. The Facebook pages impersonate ChatGPT, Google Bard, Midjourney, Jasper, and more.
Thinking through the good, the bad, and the ugly now is a process that affords us “the negative focus to survive, but a positive one to thrive.”
The post The Good, the Bad and the Ugly of Generative AI appeared first on SecurityWeek.
[Sponsored] Having digital technologies with silicon at their heart is how kinetic platforms like ships, planes, and next-generation ground vehicles become smart.