"Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers
NegativeArtificial Intelligence
A recent investigation highlights a troubling trend in the use of AI for reviewing scientific papers, where hidden prompts are injected into texts to skew evaluations positively. This manipulation raises ethical concerns about the integrity of academic reviews and the reliability of AI systems in critical assessments. As AI continues to play a significant role in academia, understanding and addressing these vulnerabilities is crucial to maintain trust in the review process.
— Curated by the World Pulse Now AI Editorial System






