Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xiaoke Yang

Xiaoke Yang

4 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

Crypto×4AI×3ML×2

Frequent co-authors

Ziyang You4×
Xuxing Lu4×
Huilong He2×
Liling Zheng1×
Zhanling Fan1×
Feng Guo1×

Research Timeline

2026
Seed Hijacking of LLM Sampling and Quantum Random Number Defense

The paper introduces SeedHijack, a backdoor attack that manipulates the pseudorandom number generation process in LLMs to force specific token selections, and proposes a hardware quantum random number generator (QRNG) as a robust defense.

DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense

The paper introduces DiffusionHijack, a supply-chain backdoor attack that compromises the PRNG used by diffusion models to deterministically control generated images, which is successfully mitigated by replacing the PRNG with a quantum random number generator (QRNG).

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

The paper introduces SeedHijack, a novel, undetectable supply-chain attack that biases LLM watermarking signals by hijacking the underlying PRNG, thereby amplifying the watermark without altering the generated text or triggering detection.

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

The paper introduces SeedHijack, a novel, undetectable supply-chain attack that biases LLM watermarking signals by hijacking the underlying Pseudo-Random Number Generator (PRNG) without altering the generated text.

Highlighted terms show continued research focus across papers

Papers

cs.CRcs.AIRecentMay 27, 2026

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

Ziyang You, Huilong He, Xiaoke Yang, Xuxing Lu

The paper introduces SeedHijack, a novel, undetectable supply-chain attack that biases LLM watermarking signals by hijacking the underlying PRNG, thereby amplifying the watermark without altering the…

View →
cs.CRcs.AIRecentMay 27, 2026

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

Ziyang You, Huilong He, Xiaoke Yang, Xuxing Lu

The paper introduces SeedHijack, a novel, undetectable supply-chain attack that biases LLM watermarking signals by hijacking the underlying Pseudo-Random Number Generator (PRNG) without altering the g…

View →
cs.CRcs.LGRecentMay 13, 2026

DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense

Ziyang You, Liling Zheng, Xiaoke Yang, Xuxing Lu

The paper introduces DiffusionHijack, a supply-chain backdoor attack that compromises the PRNG used by diffusion models to deterministically control generated images, which is successfully mitigated b…

View →
cs.CRcs.AIcs.LGRecentMay 8, 2026

Seed Hijacking of LLM Sampling and Quantum Random Number Defense

Ziyang You, Xiaoke Yang, Zhanling Fan, Feng Guo +2 more

The paper introduces SeedHijack, a backdoor attack that manipulates the pseudorandom number generation process in LLMs to force specific token selections, and proposes a hardware quantum random number…

View →