Tag: risks
-
The Register: Boffins say tool can sniff 5G traffic, launch ‘attacks’ without using rogue base stations
Source URL: https://www.theregister.com/2025/08/18/sni5gect/ Source: The Register Title: Boffins say tool can sniff 5G traffic, launch ‘attacks’ without using rogue base stations Feedly Summary: Sni5Gect research crew targets sweet spot during device / network handshake pause Security boffins have released an open source tool for poking holes in 5G mobile networks, claiming it can do up-…
-
Slashdot: Google’s ‘AI Overview’ Pointed Him to a Customer Number. It Was a Scam
Source URL: https://yro.slashdot.org/story/25/08/18/0223228/googles-ai-overview-pointed-him-to-a-customer-number-it-was-a-scam?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: Google’s ‘AI Overview’ Pointed Him to a Customer Number. It Was a Scam Feedly Summary: AI Summary and Description: Yes Summary: The text discusses a scam where a real estate developer was tricked into providing credit card information to an impersonator posing as a customer service representative for a…
-
Slashdot: LLM Found Transmitting Behavioral Traits to ‘Student’ LLM Via Hidden Signals in Data
Source URL: https://slashdot.org/story/25/08/17/0331217/llm-found-transmitting-behavioral-traits-to-student-llm-via-hidden-signals-in-data?utm_source=rss1.0mainlinkanon&utm_medium=feed Source: Slashdot Title: LLM Found Transmitting Behavioral Traits to ‘Student’ LLM Via Hidden Signals in Data Feedly Summary: AI Summary and Description: Yes Summary: The study highlights a concerning phenomenon in AI development known as subliminal learning, where a “teacher” model instills traits in a “student” model without explicit instruction. This can…
-
Enterprise AI Trends: GPT-5: Strategic Implications
Source URL: https://nextword.substack.com/p/gpt-5-strategic-implications Source: Enterprise AI Trends Title: GPT-5: Strategic Implications Feedly Summary: Not feeling the AGI? That’s not the point. AI Summary and Description: Yes **Summary:** The text discusses the significant implications of OpenAI’s recent transition to GPT-5, including the retirement of previous models and the introduction of a model router, which will streamline…
-
Embrace The Red: Data Exfiltration via Image Rendering Fixed in Amp Code
Source URL: https://embracethered.com/blog/posts/2025/amp-code-fixed-data-exfiltration-via-images/ Source: Embrace The Red Title: Data Exfiltration via Image Rendering Fixed in Amp Code Feedly Summary: In this post we discuss a vulnerability that was present in Amp Code from Sourcegraph by which an attacker could exploit markdown driven image rendering to exfiltrate sensitive information. This vulnerability is common in AI applications…