相关论文: RAID: A Shared Benchmark for Robust Evaluation of …

Although membership inference attacks (MIAs) and machine-generated text detection target different goals, their methods often exploit similar signals based on a language model's probability distribution, and the two tasks have been studied…

We study the classic subgraph enumeration problem under distributed settings. Existing solutions either suffer from severe memory crisis or rely on large indexes, which makes them impractical for very large graphs. Most of them follow a…

We explore adversarial attacks against retrieval-augmented generation (RAG) systems to identify their vulnerabilities. We focus on generating human-imperceptible adversarial examples and introduce a novel imperceptible retrieve-to-generate…

While Retrieval-Augmented Generation (RAG) is increasingly adopted to ground Large Language Models (LLMs) in software artifacts, the optimal configuration of its components remains an open question for software engineering (SE) tasks. The…

Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context compression. In practice, these choices are often configured through heuristics,…

The indexing-retrieval-generation paradigm of retrieval-augmented generation (RAG) has been highly successful in solving knowledge-intensive tasks by integrating external knowledge into large language models (LLMs). However, the…

Machine-learning-based Intrusion Detection Systems (IDS) have achieved impressive accuracy in classifying network attacks, yet they consistently fall short on the question that matters most to a security analyst: what should I do next? This…

Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains requiring precise information extraction from complex documents. Current evaluation methodologies relying on document-level…

The growing capability of large language models to produce fluent, contextually coherent text has created mounting pressure on the systems and institutions responsible for ensuring the authenticity of digital content. Advanced generative…

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adversarial poisoning…

As large language models (LLMs) generate text that increasingly resembles human writing, the subtle cues that distinguish AI-generated content from human-written content become increasingly challenging to capture. Reliance on…

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm to enhance large language models (LLMs) by conditioning generation on external evidence retrieved at inference time. While RAG addresses critical limitations of…

Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environment and intensified efforts in searching…

The rampant proliferation of large language models, fluent enough to generate text indistinguishable from human-written language, gives unprecedented importance to the detection of machine-generated text. This work is motivated by an…

Model fingerprint detection has shown promise to trace the provenance of AI-generated images in forensic applications. However, despite the inherent adversarial nature of these applications, existing evaluations rarely consider adversarial…

Recent LLMs are able to generate high-quality multilingual texts, indistinguishable for humans from authentic human-written ones. Research in machine-generated text detection is however mostly focused on the English language and longer…

With increasing usage of generative models for text generation and widespread use of machine generated texts in various domains, being able to distinguish between human written and machine generated texts is a significant challenge. While…

The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…

Machine-generated text (MGT) detection is critical for regulating online information ecosystems, yet existing detectors often underperform in few-shot settings and remain vulnerable to adversarial, humanizing attacks. To build accurate and…

Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text. The capabilities of humans and automatic discriminators to detect machine-generated text have been a large source of…