Related papers: Controllable Fake Document Infilling for Cyber Dec…
The threat that online fake news and misinformation pose to democracy, justice, public confidence, and especially to vulnerable populations, has led to a sharp increase in the need for fake news detection and intervention. Whether…
We present a collection of algorithms to filter a stream of documents in such a way that the filtered documents will cover as well as possible the interest of a person, keeping in mind that, at any given time, the offered documents should…
Large language models are evolving from single-turn responders into tool-using agents capable of sustained reasoning and decision-making for deep research. Prevailing systems adopt a linear pipeline of plan to search to write to a report,…
Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cognitively grounded irregularities that characterize human…
Large language models can deceive by subtly manipulating truthful information -- omitting key facts, shifting focus, or obscuring meaning -- making such behavior difficult to detect. Existing black-box methods rely on coarse-grained…
The rapid spread of fake news across multimedia platforms presents serious challenges to information credibility. In this paper, we propose a Debunk-and-Infer framework for Fake News Detection(DIFND) that leverages debunking knowledge to…
This paper studies physical consequences of unobservable false data injection (FDI) attacks designed only with information inside a sub-network of the power system. The goal of this attack is to overload a chosen target line without being…
Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained models, substantial amounts of hallucinated…
Recent advances in large language models (LLMs) have enabled the large-scale generation of highly fluent and deceptive news-like content. While prior work has often treated fake news detection as a binary classification problem, modern fake…
The widespread dissemination of fake news on social media poses significant risks, necessitating timely and accurate detection. However, existing methods struggle with unseen news due to their reliance on training data from past events and…
Researchers produce thousands of scholarly documents containing valuable technical knowledge. The community faces the laborious task of reading these documents to identify, extract, and synthesize information. To automate information…
The rapid spread of misinformation in the digital era poses significant challenges to public discourse, necessitating robust and scalable fact-checking solutions. Traditional human-led fact-checking methods, while credible, struggle with…
Previous studies in deepfake detection have shown promising results when testing face forgeries from the same dataset as the training. However, the problem remains challenging when one tries to generalize the detector to forgeries from…
Recent DeepFake detection methods have shown excellent performance on public datasets but are significantly degraded on new forgeries. Solving this problem is important, as new forgeries emerge daily with the continuously evolving…
We present a simple approach for text infilling, the task of predicting missing spans of text at any position in a document. While infilling could enable rich functionality especially for writing assistance tools, more attention has been…
Machine learning models are widely used in real-world applications. However, their complexity makes it often challenging to interpret the rationale behind their decisions. Counterfactual explanations (CEs) have emerged as a viable solution…
Hidden LLM prompts have appeared in online documents with increasing frequency. Their goal is to trigger indirect prompt injection attacks while remaining undetected from human oversight, to manipulate LLM-powered automated document…
Detecting euphemisms is essential for content security on various social media platforms, but existing methods designed for detecting euphemisms are ineffective in impromptu euphemisms. In this work, we make a first attempt to an…
Honeyfiles are security assets designed to attract and detect intruders on compromised systems. Honeyfiles are a type of honeypot that mimic real, sensitive documents, creating the illusion of the presence of valuable data. Interaction with…
Motivated by many existing security and privacy applications, e.g., network traffic attribution, linkage attacks, private web search, and feature-based data de-anonymization, in this paper, we study the Feature-based Data Inferability (FDI)…