2026
RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse
ICML 2026poster
Large Language Models (LLMs) are increasingly vulnerable to *Prompt Injection (PI)* attacks, where adversarial instructions hidden within retrieved contexts hijack the model's execution flow. Current defenses typically face a critical trade-off: *prevention-based* fine-tuning often degrades general …