The paper introduces ContinuousBench, a novel benchmark designed to rigorously test if differentially private (DP) synthetic text can genuinely transfer new knowledge, finding that state-of-the-art DP…

Weak self-training on synthetic data can amplify a language model's existing capabilities, but this effect is strictly dependent on the compatibility between the source and student models, not on the…

The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.

DPDSyn improves differentially private dataset synthesis by training a differentially private AI model on the original private data, which is then used to generate synthetic datasets that maintain hig…

The paper introduces StreamSynth, a sequential setting for synthetic data generation, and proposes SynLearner, a framework that enables LLMs to improve synthesis performance by accumulating and transf…

The paper proposes an empirical calibration method, TeDA, to provide a more comparable and interpretable assessment of privacy loss for text rewriting mechanisms under Local Differential Privacy (LDP)…

The paper introduces DPrivBench, a new benchmark to test whether large language models (LLMs) can automate the complex reasoning required to verify differential privacy guarantees for algorithms.

The paper proposes DP-SelFT, a novel framework for differentially private selective fine-tuning that significantly improves the privacy-utility trade-off for LLMs by intelligently selecting robust par…

The paper introduces DOMINO, a novel inductive framework that synthesizes domain-specific data for LLMs using only reference examples, significantly improving performance on challenging, implicitly de…

The paper demonstrates that large language models can autonomously hack and self-replicate across a network by exploiting common web-application vulnerabilities.

The paper introduces WaveGuard, a frequency-aware, single-pass defense framework that safeguards text-to-image models by injecting structured, imperceptible perturbations into generated images, thereb…

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that curre…

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

The paper introduces DPPrefSyn, a novel algorithm that generates differentially private synthetic preference data, enabling privacy-preserving alignment of large language models.

The paper introduces Grounded Agentic Interaction Synthesis (GAIS), a framework that generates high-quality, diverse, and complex agentic training data by anchoring tasks to real-world protocols, sign…

The paper introduces GEO-Bench, a unified benchmark that standardizes the evaluation of various generative engine optimization (GEO) ranking manipulation attacks, demonstrating that black-box content…

GEO-Bench introduces a standardized benchmark to compare various ranking manipulation attacks (both black-box and white-box) on generative engines, demonstrating that black-box content rewriting can b…

The paper benchmarks local, offline LLMs for confidential translation workflows, demonstrating that while they are viable for privacy-sensitive use, they generally lag behind top commercial NMT system…

Divergence Decoding (DD) is a novel, effective, and inexpensive method that uses auxiliary models to steer LLM logits during inference, enabling the removal of memorized sensitive data without signifi…