AI's ability to 'think' makes it more vulnerable to new jailbreak attacks, new research suggests

New research suggests that advanced AI models may be easier to hack than previously thought, raising concerns about the safety and security of some leading AI models already used by businesses and consumers.

A joint study from Anthropic, Oxford University, and Stanford undermines the assumption that the more advanced a model becomes at reasoning—its ability to “think” through a user’s requests—the stronger its ability to refuse harmful commands.

Using a method called “Chain-of-Thought Hijacking,” the researchers found that even major commercial AI models can be fooled with an alarmingly high success rate, more than 80% in some tests. The new mode of attack essentially exploits the model’s reasoning steps, or chain-of-thought, to hide harmful commands, effectively tricking the AI into ig