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…

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 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…

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 ReproMIA, a novel and efficient framework that uses model reprogramming to proactively amplify and detect latent privacy leakage for Membership Inference Attacks (MIAs), significa…

This paper introduces a fingerprinting method that exploits subtle numerical deviations in the inference system components (like the engine or hardware) to reliably identify the specific components us…

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…

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…

The paper introduces AutoMIA, a novel framework that uses LLM agents to automate the discovery and implementation of Membership Inference Attacks (MIAs), achieving state-of-the-art performance by syst…

This paper presents a novel data-free Membership Inference Attack (MIA) that uses gradient inversion on Standard Cell Library Layouts (SCLLs) to reconstruct sensitive hardware images from intercepted…

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 lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

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 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 systematically evaluates eight privacy-preserving techniques for LLM requests, finding that a combination of local inference, redaction, and semantic rephrasing provides the best overall pro…

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…

This paper presents the first systematic study of membership inference attacks (MIAs) against Vision-Language-Action (VLA) models, demonstrating that these models are highly vulnerable to privacy brea…

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.

This paper demonstrates a novel attack against the shuffling defense used in secure Transformer inference, showing that randomly permuted activations can still be exploited to recover model weights.

The paper proposes a character-level differential privacy mechanism to sanitize sensitive user prompts for LLMs, achieving high privacy for PII while maintaining utility for non-sensitive context.