Tag: ai safety
AI gives the game away
The latest threat for companies using large language (LLM) AI software to replace human staff is the software’s innate gullibility. LLM software can be likened to some cowardly bank clerk in an old Western hold-up who not only willingly opens a back door for the bad guys but also willingly tells them the combination of the safe. The methods for persuading LLMs into naively disclosing the keys to the corporate kingdom are known as ‘LLM Jailbreak’ techniques. Palo Alto Networks Unit 42 researchers have named one such LLM Jailbreak, “Bad Likert Judge”.
Russian Campaign Targeting UK Politics Exposed – December 8th
The National Cyber Security Centre (NCSC) in collaboration with partners from the US, Australia, Canada, and New Zealand revealed the Russian-state-backed threat actors terrorizing UK political systems. The NCSC identified the group 'Star Blizzard' to be a subordinate to Centre 18 from the Russian Federal Security Service (FSB). Star Blizzard targeted UK parliamentarians, UK-US trade documents, UK think tanks, universities, journalists, and NGOs using various sophisticated phishing tactics.