5 papers
AdaForensics: Learning A Characteristic-aware Adaptive Deepfake Detector
Xiaoke Yang, Haixu Song, Xiangyu Lu +2
In this paper, we propose a characteristic-aware adaptive network named AdaForensics for deepfake detection. Most existing methods learn a fixed network to detect deepfakes based o…
UniqueSplat: View-conditioned 3D Gaussian Splatting for Generalizable 3D Reconstruction
Haixu Song, Xiaoke Yang, Shengjun Zhang +2
In this paper, we propose UniqueSplat, a view-conditioned feed-forward 3D Gaussian Splatting model to reconstruct customized 3D radiance fields for each view query. Existing feed-f…
Blind PRNG Hijacking: An Undetectable Integrity-Preserving Attack Against LLM Watermarking
Ziyang You, Huilong He, Xiaoke Yang +1
Cryptographic watermarking is a leading defense for attributing text generated by large language models (LLMs). Existing schemes, including KGW, Unigram, and DipMark, derive their…
DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense
Ziyang You, Liling Zheng, Xiaoke Yang +1
Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor attack that hijacks the PRNG to de…
Seed Hijacking of LLM Sampling and Quantum Random Number Defense
Ziyang You, Xiaoke Yang, Zhanling Fan +3
Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chain attack surface overlooked by…