The paper introduces a Contextual Integrity (CI) framework and a new benchmark (DelegateCI-Bench) to rewrite user queries sent to cloud LLMs, ensuring only task-essential information is retained while…

The paper proposes a novel test-driven pipeline that simulates realistic code generation scenarios to detect privacy leaks in LLMs, achieving a 2.56x increase in detected leakage compared to existing…

The paper introduces an automated framework demonstrating that LLM system instructions are vulnerable to encoding attacks, where structured output requests can bypass safety refusals and leak sensitiv…

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…

The paper introduces Privacy-Preserving Fine-Tuning (PPFT), a novel two-stage pipeline that allows LLMs to process sensitive data via pooled embeddings rather than raw text, achieving a strong balance…

CachePrune introduces a privacy-aware, fine-grained KV cache sharing mechanism that allows LLM inference systems to safely reuse cache entries across users' requests, significantly improving efficienc…

SharedRequest introduces a model-agnostic framework that enhances LLM privacy and efficiency by batching and mixing prompts with noisy variants, achieving high utility and significant cost reduction.

The paper introduces a novel framework using steganographic canary files to detect and block unauthorized processing of sensitive documents by LLMs, even when the data passes through traditional secur…

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 introduces $(l, b)$-inextractability, a new formal measure that demonstrates that standard indistinguishability properties are insufficient for guaranteeing protection against data extractio…

The paper proposes CAMP, a cross-turn privacy framework that mitigates Cumulative PII Exposure (CPE) in multi-turn LLM conversations by tracking and masking accumulated personal data across the entire…

This paper investigates how Byte-Pair Encoding (BPE) tokenization causes Code LLMs to disproportionately memorize certain types of secrets, a phenomenon termed 'gibberish bias'.

The paper introduces HERALD, a token-level cryptographic redaction framework that encrypts only sensitive tokens in clinical text, enabling privacy-preserving LLM deployment without significant loss o…

This paper develops provably undetectable and robust watermarking schemes for LLM outputs even when the per-token entropy is only constant, removing previous dependencies on high entropy rates or larg…

The paper introduces a systematic benchmark to test LLMs' ability to recover Indicators of Compromise (IoCs) from JavaScript code, finding that while LLMs handle simple obfuscation well, encryption-ba…

The paper proposes PPRoute, a privacy-preserving LLM routing framework that significantly speeds up secure model selection while maintaining high performance comparable to non-private methods.

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 proposes ADAM, a novel and highly effective privacy attack that systematically extracts sensitive data from LLM agent memory by adaptively querying the victim agent's memory based on data di…

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…

The paper introduces CIPL, a unified channel-oriented framework, demonstrating that privacy leakage in LLM agents is governed by observable data channels and pipeline interactions, rather than being l…