AgentLSD: Evaluating AI Security Agents Under Adversarial Task Contamination
AgentLSD benchmark shows deceptive CTF artifacts like fake flags and decoy endpoints steer AI security agents wrong, inflating turns and tokens.
1 stories, newest first · one card per story
AgentLSD benchmark shows deceptive CTF artifacts like fake flags and decoy endpoints steer AI security agents wrong, inflating turns and tokens.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views