Megadose AI progress, ranked and analyzed.

Researchers detail "context bombing", where defenders use prompt injections to trigger guardrails of attackers' LLMs, cutting AI hacking success rates by ~90% (Dan Goodin/Ars Technica)

Techmeme ·

Researchers introduced context bombing, a defensive prompt-injection technique that reportedly cuts LLM-assisted hacking success rates by about 90%.

Categories: Research

Excerpt

Dan Goodin / Ars Technica: Researchers detail “context bombing”, where defenders use prompt injections to trigger guardrails of attackers' LLMs, cutting AI hacking success rates by ~90% — Prompt injections, the malicious commands attackers embed into content to entice large language models to follow them …