Csiszar's formulation of the $f$-divergence introduced a vast family of functionals for quantifying dissimilarity between probability distributions. However, many applications in statistics and information theory rely only on a few $f$-divergences, such as the Kullback-Leibler divergence, the $\chi^2$-divergence, and t...
This work recast black-box black-box LLM steganography as a sequential communication problem with causal, noiseless feedback: every generated token is observed by both parties and can guide subsequent embedding.
Si-Dong Guo, Sajani Vithana, Atefeh Gilani et al.· 1 citation
This work considers normalized histograms as distribution estimators and characterize the asymptotically optimal domain-aware privacy mechanism within a specific class of DP mechanisms, and introduces PubMix, a public-data-aware DP mechanism that can be used in histogram-based data synthesis pipelines.
Sajani Vithana, Sangwon Jung, Haoyang Hu et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.