Related papers: What's a little leakage between friends?

Split Learning (SL) is a collaborative learning approach that improves privacy by keeping data on the client-side while sharing only the intermediate output with a server. However, the distributed nature of SL introduces new security…

For privacy concerns to be addressed adequately in current machine learning systems, the knowledge gap between the machine learning and privacy communities must be bridged. This article aims to provide an introduction to the intersection of…

In this paper, we first introduce the notion of channel leakage as the minimum mutual information between the channel input and channel output. As its name indicates, channel leakage quantifies the minimum information leakage to the…

Covert communication has become an important area of research in computer security. It involves hiding specific information on a carrier for message transmission and is often used to transmit private data, military secrets, and even…

Adversarial examples crafted by an explicit adversary have attracted significant attention in machine learning. However, the security risk posed by a potential false friend has been largely overlooked. In this paper, we unveil the threat of…

Privacy is an increasingly important aspect of data publishing. Reasoning about privacy, however, is fraught with pitfalls. One of the most significant is the auxiliary information (also called external knowledge, background knowledge, or…

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…

Growing at a fast pace, modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems. Sharing information and distributing workloads allow autonomous agents to better perform tasks…

The ability to accurately predict cyber-attacks would enable organizations to mitigate their growing threat and avert the financial losses and disruptions they cause. But how predictable are cyber-attacks? Researchers have attempted to…

This article provides a quantitative analysis of privacy-compromising mechanisms on 1 million popular websites. Findings indicate that nearly 9 in 10 websites leak user data to parties of which the user is likely unaware; more than 6 in 10…

Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and…

Nonlinear aggregation is central to modern distributed systems, yet its privacy behavior is far less understood than that of linear aggregation. Unlike linear aggregation where mature mechanisms can often suppress information leakage,…

Model distillation is frequently proposed as a technique to reduce the privacy leakage of machine learning. These empirical privacy defenses rely on the intuition that distilled ``student'' models protect the privacy of training data, as…

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

In this work, we propose information laundering, a novel framework for enhancing model privacy. Unlike data privacy that concerns the protection of raw data information, model privacy aims to protect an already-learned model that is to be…

Super-apps have emerged as comprehensive platforms integrating various mini-apps to provide diverse services. While super-apps offer convenience and enriched functionality, they can introduce new privacy risks. This paper reveals a new…

Cyber deception is one of the key approaches used to mislead attackers by hiding or providing inaccurate system information. There are two main factors limiting the real-world application of existing cyber deception approaches. The first…

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone…

We study the information leakage to a guessing adversary in index coding with a general message distribution. Under both vanishing-error and zero-error decoding assumptions, we develop lower and upper bounds on the optimal leakage rate,…

As a practical privacy-preserving learning method, split learning has drawn much attention in academia and industry. However, its security is constantly being questioned since the intermediate results are shared during training and…