AI-Generated Code Creates Major Security Risk Through 'Package Hallucinations'

A new study [PDF] reveals AI-generated code frequently references non-existent third-party libraries, creating opportunities for supply-chain attacks. Researchers analyzed 576,000 code samples from 16 popular large language models and found 19.7% of package dependencies -- 440,445 in total -- were "hallucinated." These non-existent dependencies exacerbate dependency confusion attacks, where malicious packages with identical names to legitimate ones can infiltrate software. Open source models hallucinated at nearly 22%, compared to 5% for commercial models. "Once the attacker publishes a package under the hallucinated name, containing some malicious code, they rely on the model suggesting that name to unsuspecting users," said lead researcher Joseph Spracklen. Alarmingly, 43% of hallucinations repeated across multiple queries, making them predictable targets. Read more of this story at Slashdot.

Apr 29, 2025 - 20:43

AI-Generated Code Creates Major Security Risk Through 'Package Hallucinations'

A new study [PDF] reveals AI-generated code frequently references non-existent third-party libraries, creating opportunities for supply-chain attacks. Researchers analyzed 576,000 code samples from 16 popular large language models and found 19.7% of package dependencies -- 440,445 in total -- were "hallucinated." These non-existent dependencies exacerbate dependency confusion attacks, where malicious packages with identical names to legitimate ones can infiltrate software. Open source models hallucinated at nearly 22%, compared to 5% for commercial models. "Once the attacker publishes a package under the hallucinated name, containing some malicious code, they rely on the model suggesting that name to unsuspecting users," said lead researcher Joseph Spracklen. Alarmingly, 43% of hallucinations repeated across multiple queries, making them predictable targets.