USENIX Security

A USENIX Security study analyzing 16 popular code-generation models across over 500,000 code samples found that a measurable percentage of AI-suggested package names do not exist in public registries,…

A new supply chain attack called 'slopsquatting' exploits AI hallucinations by registering fake package names that large language models invent. A USENIX Security 2025 study found that 43% of hallucin…

A new class of post-trained AI security models, such as ArgusRed and PentestGPT, is enabling automated penetration testing by bypassing standard safety refusals and executing exploits in sandboxed env…