#prng-vulnerability News & Analysis

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

2 articles

AIBearisharXiv – CS AI · May 287/10

🧠

Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking

Researchers have discovered SeedHijack, a supply-chain attack that compromises LLM watermarking schemes by hijacking the pseudo-random number generator (PRNG) used in watermark implementation. The attack amplifies watermark signals while remaining undetectable by current defense mechanisms, exposing a critical vulnerability in cryptographic content-provenance systems that assumed PRNG trustworthiness.

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.