相关论文: Protecting De-identified Documents from Search-bas…

Retrieval-Augmented Generation (RAG) is a promising technique for applying LLMs to proprietary domains. However, retrieved documents may contain sensitive knowledge, posing risks of privacy leakage in generative results. Thus, effectively…

In this work, we focus on protection against identity disclosure in the publication of sparse multidimensional data. Existing multidimensional anonymization techniquesa) protect the privacy of users either by altering the set of…

Network embedding represents network nodes by a low-dimensional informative vector. While it is generally effective for various downstream tasks, it may leak some private information of networks, such as hidden private links. In this work,…

When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As…

Graph Neural Networks (GNNs) are widely used and deployed for graph-based prediction tasks. However, as good as GNNs are for learning graph data, they also come with the risk of privacy leakage. For instance, an attacker can run carefully…

Large language models (LLMs) are increasingly integrated into real-world personalized applications through retrieval-augmented generation (RAG) mechanisms to supplement their responses with domain-specific knowledge. However, the valuable…

Ensuring that online discussions are civil and productive is a major challenge for social media platforms. Such platforms usually rely both on users and on automated detection tools to flag inappropriate arguments of other users, which…

Reconstruction attacks and defenses are essential in understanding the data leakage problem in machine learning. However, prior work has centered around empirical observations of gradient inversion attacks, lacks theoretical grounding, and…

Confidentiality of the data is being endangered as it has been categorized into false categories which might get leaked to an unauthorized party. For this reason, various organizations are mainly implementing data leakage prevention systems…

Retrieval-augmented generation and tool-integrated LLM agents increasingly depend on external textual sources. This reliance broadens the available attack surface, allowing adversaries to insert malicious instructions that trigger…

To mitigate the potential harms of Large Language Models (LLMs)generated text, researchers have proposed watermarking, a process of embedding detectable signals within text. With watermarking, we can always accurately detect LLM-generated…

High-quality paraphrases are easy to produce using instruction-tuned language models or specialized paraphrasing models. Although this capability has a variety of benign applications, paraphrasing attacks$\unicode{x2013}$paraphrases applied…

Online disinformation poses a global challenge, placing significant demands on fact-checkers who must verify claims efficiently to prevent the spread of false information. A major issue in this process is the redundant verification of…

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…

Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract…

This paper presents a link analysis approach for identifying privileged documents by constructing a network of human entities derived from email header metadata. Entities are classified as either counsel or non-counsel based on a predefined…

Our ability to control the flow of sensitive personal information to online systems is key to trust in personal privacy on the internet. We ask how to detect, assess and defend user privacy in the face of search engine personalisation? We…

Prompt injection attacks are an emerging threat to large language models (LLMs), enabling malicious users to manipulate outputs through carefully designed inputs. Existing detection approaches often require centralizing prompt data,…

With the widespread adoption of Large Language Models (LLMs), jailbreak attacks have become an increasingly pressing safety concern. While safety-aligned LLMs can effectively defend against normal harmful queries, they remain vulnerable to…

A lot of manual work goes into identifying a topic for an article. With a large volume of articles, the manual process can be exhausting. Our approach aims to address this issue by automatically extracting topics from the text of large…