This paper conducts a structured ablation study using a unified threat model to evaluate how various system factors (like model architecture and retrieval configuration) influence different types of p…

This survey provides a comprehensive, structured taxonomy of split learning techniques for fine-tuning Large Language Models (LLMs), covering model optimization, system efficiency, and privacy preserv…

The paper establishes a standardized security assessment framework and develops a multi-layered defensive system, demonstrating that systematic testing and external defenses are crucial for safe LLM d…

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.

SafeLM is a comprehensive framework that jointly addresses privacy, security, misinformation, and adversarial robustness in federated LLMs, achieving high safety performance while significantly reduci…

This paper introduces Swiss-Bench 003, an expanded evaluation framework assessing LLM reliability and adversarial security across eight dimensions using 808 Swiss-specific items, revealing that self-g…

The paper quantifies the cost of privacy in language identification and generation using differentially private (DP) methods, finding that the cost is surprisingly mild, particularly absent under appr…

This paper corrects the theoretical analysis of DP-SGD by identifying that common implementations, which use batch averaging, result in weaker privacy guarantees than previously reported.

The paper introduces SIGIL, a novel framework that cryptographically seals the entire lifecycle of LLM skills, ensuring verifiable integrity from publication through runtime execution to prevent suppl…

RouteScan introduces a non-intrusive framework that audits the safety of Mixture-of-Experts (MoE) LLMs by analyzing low-level GPU expert routing telemetry, achieving high accuracy even on unseen harmf…

The paper demonstrates that encoding harmful prompts as genuine mathematical problems, rather than just using mathematical formatting, effectively bypasses the safety filters of large language models.

The paper introduces a Privacy Policy Enforcement (PPE) framework using dual one-class density estimators to detect contextual data leakage in Retrieval-Augmented Generation (RAG) systems, achieving h…

The paper introduces a 'Privacy Guard' framework that simultaneously reduces operational costs and eliminates data leakage risks when using LLMs by optimizing prompts and routing queries to secure mod…

This paper analyzes the reliability of efficient membership inference attack (MIA) evaluation methods, demonstrating that standard aggregation techniques introduce biases that compromise accurate vuln…

The paper proposes an attestation-aware promotion gate to mitigate supply-chain risks in LLM pipelines by cryptographically verifying and enforcing claims about training and release artifacts before d…

This paper addresses the vulnerability of existing LLM safety monitors to adaptive attackers and proposes activation watermarking, a technique that significantly improves detection robustness against…

LLM-FACETS introduces an open-source, privacy-preserving framework designed to enable non-technical domain experts and compliance officers to audit and evaluate the transparency and accountability of…

The paper introduces a Gaussian Differential Privacy (GDP)-based auditing framework to provide the first tight audits of privacy guarantees for state-of-the-art synthetic data generators like MST and…

The paper introduces the PrivacyIceberg framework to systematically categorize and empirically demonstrate the high risk of automated, deep personal profiling using LLM agents, revealing a significant…

The paper introduces an efficient, lightweight LLM framework for smart contract auditing that decouples the audit process into multiple components, achieving high accuracy while significantly reducing…