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

Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions. However, all existing certified defense methods assume that the defenders are…

LLMs cannot reliably recognize their parametric knowledge boundaries and often hallucinate answers to outside-of-boundary questions. In this paper, we introduce MASH (Modeling Abstention via Selective Help-seeking), a training framework…

Large Language Models (LLMs) have achieved human-level fluency in text generation, making it difficult to distinguish between human-written and LLM-generated texts. This poses a growing risk of misuse of LLMs and demands the development of…

Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These attacks,…

Executing large test suites is time and resource consuming, sometimes impossible, and such test suites typically contain many redundant test cases. Hence, test case minimization is used to remove redundant test cases that are unlikely to…

Neural text detectors aim to decide the characteristics that distinguish neural (machine-generated) from human texts. To challenge such detectors, adversarial attacks can alter the statistical characteristics of the generated text, making…

Nowadays, powerful large language models (LLMs) such as ChatGPT have demonstrated revolutionary power in a variety of tasks. Consequently, the detection of machine-generated texts (MGTs) is becoming increasingly crucial as LLMs become more…

Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure. Conversely,…

In this paper, a tool for detecting LLM AI text generation is developed based on the Transformer model, aiming to improve the accuracy of AI text generation detection and provide reference for subsequent research. Firstly the text is…

Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge bases, but this advancement introduces significant privacy risks. Existing privacy attacks on RAG systems can trigger data…

Advanced large language models (LLMs) can generate text almost indistinguishable from human-written text, highlighting the importance of LLM-generated text detection. However, current zero-shot techniques face challenges as white-box…

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

Arbitrary-shaped text detection is an important and challenging task in computer vision. Most existing methods require heavy data labeling efforts to produce polygon-level text region labels for supervised training. In order to reduce the…

With the continuous advancement of generative models, face morphing attacks have become a significant challenge for existing face verification systems due to their potential use in identity fraud and other malicious activities. Contemporary…

Contrastive explanations for understanding the behavior of black box models has gained a lot of attention recently as they provide potential for recourse. In this paper, we propose a method Contrastive Attributed explanations for Text (CAT)…

The rise of agentic AI systems, where agents collaborate to perform diverse tasks, poses new challenges with observing, analyzing and optimizing their behavior. Traditional evaluation and benchmarking approaches struggle to handle the…

Existing AI-generated text detection methods heavily depend on large annotated datasets and external threshold tuning, restricting interpretability, adaptability, and zero-shot effectiveness. To address these limitations, we propose…

Many AI detection models have been developed to counter the presence of articles created by artificial intelligence (AI). However, if a human-authored article is slightly polished by AI, a shift will occur in the borderline decision of…

Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting,…