There are at least two kinds of catastrophe scenarios, and both are getting more plausible

Large Language Models (LLM) have made amazing progress in recent years. Most recently, they have demonstrated to answer natural language questions at a surprising performance level. In addition, by clever prompting, these models can change their behavior. In this way, these models blur the line between data and instruction. From "traditional" cybersecurity, we know that this is a problem. The importance of security boundaries between trusted and untrusted inputs for LLMs was underestimated. We show that Prompt Injection is a serious security threat that needs to be addressed as models are deployed to new use-cases and interface with more systems. [PDF DOC] https://arxiv.org/pdf/2302.12173.pdf

LLaMA, Meta’s latest family of large language models, has been leaked along with its weights and is now available to download through torrents

Attackers are distributing malware disguised as a ChatGPT desktop client for Windows offering “precreated accounts”

Ever since OpenAI launched ChatGPT at the end of November, commentators on all sides have been concerned about the impact AI-driven content-creation will have, particularly in the realm of cybersecurity. In fact, many researchers are concerned that generative AI solutions will democratize cybercrime.

The way that many of our systems currently focus on engagement makes them particularly vulnerable to the incoming wave of content from bots like GPT-3

Hackers are stealing PII to apply for remote jobs and then using deepfakes to pass the interview.

For years, activists and academics have been raising concerns that facial analysis software that claims to be able to identify a person’s age, gender and emotional state can be biased, unreliable or invasive — and shouldn’t be sold.

The way that many of our systems currently focus on engagement makes them particularly vulnerable to the incoming wave of content from bots like GPT-3

Hackers are stealing PII to apply for remote jobs and then using deepfakes to pass the interview.

For years, activists and academics have been raising concerns that facial analysis software that claims to be able to identify a person’s age, gender and emotional state can be biased, unreliable or invasive — and shouldn’t be sold.