Researchers have demonstrated that putting words in ASCII art can cause LLMs—GPT-3.5, GPT-4, Gemini, Claude, and Llama2—to ignore their safety instructions.
Research paper.
Jailbreaking LLMs with ASCII Art
March 12, 2024 0 Comments
Explore More
Friday Squid Blogging: Illex Squid and Climate Change
February 23, 2024 0 Comments
There are correlations between the populations of the Illex Argentines squid and water temperatures. As usual, you can also use this squid post to talk about the security stories in
Businesses Increase Cybersecurity as Budgets Surge in 2024
February 22, 2024 0 Comments
Over two-thirds of IT decision-makers increase cybersecurity budgets in 2024, prioritizing cloud security and incident response as cyber threats escalate
U-Haul Informs Customers of Major Data Breach
February 26, 2024 0 Comments
Moving giant U-Haul has revealed that 67,000 customers were caught in a data breach last year