A naukri.com initiative
Securelist
1M
438
Image Credit: Securelist
Loose-lipped neural networks and lazy scammers
- Loose-lipped neural networks (LLMs) enable automated writing that mimics human speech, which is useful to scammers who develop fake websites, sometimes to coincide with events such as Black Friday.
- These sites use LLMs to create unique and high-quality content that is hard to detect and analyse, often mimicking companies in dynamic industries, such as cryptocurrency.
- An LLM-generated message is detectable, however, by first-person apologies or refusals to follow instructions. Weaknesses in LLM applications can also leave tells, artifacts or indicators, that enable investigators to track fraudsters.
- Artifacts of this kind not only expose the use of LLMs to create scam web pages, but allow us to estimate both the campaign duration and the approximate time of content creation.
- LLMs can be used not only to generate text blocks, but entire web pages.
- LLM-generated text can go hand-in-hand with various techniques that hinder rule-based detection.
- As large language models improve, their strengths and weaknesses, as well as the tasks they do well or poorly, are becoming better understood. Threat actors are exploring applications of this technology in a range of automation scenarios.
- Peering into the future, we can assume that LLM-generated content will become increasingly difficult to distinguish from human-written.
- The task of automatically identifying LLM-generated text is extremely complex, especially as regards generic content like marketing materials, which are similar to what we saw in the examples.
- To better protect yourself against phishing, be it hand-made or machine-generated, it’s best to use modern security solutions that combine analysis of text information, metadata and other attributes to protect against fraud.
Read Full Article
26 Likes
For uninterrupted reading, download the app