#inference-security News & Analysis

2 articles tagged with #inference-security. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles

AIBearisharXiv – CS AI · May 127/10

🧠

Seed Hijacking of LLM Sampling and Quantum Random Number Defense

Researchers demonstrate SeedHijack, a supply-chain attack exploiting pseudorandom number generators in LLM sampling to inject arbitrary tokens without modifying model weights, achieving 99.6% success rates across multiple models. A quantum random number generator-based defense is proposed that neutralizes the attack with minimal performance overhead.

AIBullisharXiv – CS AI · Apr 107/10

🧠

ConfusionPrompt: Practical Private Inference for Online Large Language Models

Researchers introduce ConfusionPrompt, a privacy framework for large language models that decomposes user prompts into smaller sub-prompts mixed with pseudo-prompts before sending to cloud servers. The method protects user privacy while maintaining higher utility than existing perturbation-based approaches and works with existing black-box LLMs without modification.