Related papers: MASH: Evading Black-Box AI-Generated Text Detector…

Large Language Models have shown growing ability to generate fluent and coherent texts that are highly similar to the writing style of humans. Current detectors for Machine-Generated Text (MGT) perform well when they are trained and tested…

With the launch of ChatGPT, large language models (LLMs) have attracted global attention. In the realm of article writing, LLMs have witnessed extensive utilization, giving rise to concerns related to intellectual property protection,…

The integration of machine learning (ML) algorithms into Internet of Things (IoT) applications has introduced significant advantages alongside vulnerabilities to adversarial attacks, especially within IoT-based intrusion detection systems…

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 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…

Large Language Models (LLMs) have revolutionized the domain of natural language processing (NLP) with remarkable capabilities of generating human-like text responses. However, despite these advancements, several works in the existing…

With the rapid development and widespread application of Large Language Models (LLMs), the use of Machine-Generated Text (MGT) has become increasingly common, bringing with it potential risks, especially in terms of quality and integrity in…

Current large language models (LLM) provide a strong foundation for large-scale user-oriented natural language tasks. Many users can easily inject adversarial text or instructions through the user interface, thus causing LLM model security…

We present DASH (Deception-Augmented Shared mental model for Human-machine teaming), a novel framework that enhances mission resilience by embedding proactive deception into Shared Mental Models (SMM). Designed for mission-critical…

Patch-based attacks introduce a perceptible but localized change to the input that induces misclassification. A limitation of current patch-based black-box attacks is that they perform poorly for targeted attacks, and even for the less…

Facial identification systems are increasingly deployed in surveillance and yet their vulnerability to adversarial evasion and impersonation attacks pose a critical risk. This paper introduces a novel framework for generating adversarial…

Machine-generated text (MGT) detection requires identifying structurally invariant signals across generation models, rather than relying on model-specific fingerprints. In this respect, we hypothesize that while large language models excel…

Widely applied large language models (LLMs) can generate human-like content, raising concerns about the abuse of LLMs. Therefore, it is important to build strong AI-generated text (AIGT) detectors. Current works only consider document-level…

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…

In recent times, large language models (LLMs) have made significant strides in generating computer code, blurring the lines between code created by humans and code produced by artificial intelligence (AI). As these technologies evolve…

The rapid advancement of large language models (LLMs) has made detecting AI-generated text an increasingly critical challenge. Traditional methods often fail to capture the nuanced semantic differences between human and machine-generated…

While AI-generated text (AIGT) detectors achieve over 90\% accuracy on direct LLM outputs, they fail catastrophically against iteratively-paraphrased content. We investigate why iteratively-paraphrased text -- itself AI-generated -- evades…

Large language models (LLMs) have grown more powerful in language generation, producing fluent text and even imitating personal style. Yet, this ability also heightens the risk of identity impersonation. To the best of our knowledge, no…

As of recent generative adversarial networks have allowed for big leaps in the realism of generated images in diverse domains, not the least of which being handwritten text generation. The generation of realistic-looking hand-written text…

We introduce Mischief, a simple and lightweight method to produce a class of human-readable, realistic adversarial examples for language models. We perform exhaustive experimentations of our algorithm on four transformer-based…