3 papers
cs.CR2026
Forging the Unforgeable: On the Feasibility of Counterfeit Watermarks in Backdoor-Based Dataset Ownership Verification
Zhiying Li, Zhi Liu, Dongjie Liu +6
Backdoor watermarking has emerged as the predominant approach for protecting public datasets, enabling dataset ownership verification (DOV) through embedded triggers that induce pr…
cs.CR2026
BitHydra: Towards Bit-flip Inference Cost Attack against Large Language Models
Xiaobei Yan, Yiming Li, Hao Wang +2
Large language models (LLMs) are widely deployed, but their substantial compute demands make them vulnerable to inference cost attacks that aim to deliberately maximize the output…
cs.CR2026
DSSmoothing: Toward Certified Dataset Ownership Verification for Pre-trained Language Models via Dual-Space Smoothing
Ting Qiao, Xing Liu, Wenke Huang +3
Large web-scale datasets have driven the rapid advancement of pre-trained language models (PLMs), but unauthorized data usage has raised serious copyright concerns. Existing datase…