相关论文: Complete Evasion, Zero Modification: PDF Attacks o…

Existing methods for the zero-shot detection of machine-generated text are dominated by three statistical quantities: log-likelihood, log-rank, and entropy. As language models mimic the distribution of human text ever closer, this will…

While text-to-image diffusion models demonstrate impressive generation capabilities, they also exhibit vulnerability to backdoor attacks, which involve the manipulation of model outputs through malicious triggers. In this paper, for the…

Most existing algorithms for replicated lists, which are widely used in collaborative text editors, suffer from a problem: when two users concurrently insert text at the same position in the document, the merged outcome may interleave the…

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…

Backdoor attacks targeting text-to-image diffusion models have advanced rapidly. However, current backdoor samples often exhibit two key abnormalities compared to benign samples: 1) Semantic Consistency, where backdoor prompts tend to…

Modern software often accepts inputs with highly complex grammars. Recent advances in large language models (LLMs) have shown that they can be used to synthesize high-quality natural language text and code that conforms to the grammar of a…

Smart contract vulnerabilities have led to billions in losses, yet finding actionable exploits remains challenging. Traditional fuzzers rely on rigid heuristics and struggle with complex attacks, while human auditors are thorough but slow…

With the advancement in capabilities of Large Language Models (LLMs), one major step in the responsible and safe use of such LLMs is to be able to detect text generated by these models. While supervised AI-generated text detectors perform…

Large Language Models (LLMs) have demonstrated remarkable capabilities in generating text that closely resembles human writing across a wide range of styles and genres. However, such capabilities are prone to potential misuse, such as fake…

The widespread adoption of ChatGPT has raised concerns about its misuse, highlighting the need for robust detection of AI-generated text. Current word-level detectors are vulnerable to paraphrasing or simple prompts (PSP), suffer from…

Large language models (LLMs) present significant risks when used to generate non-factual content and spread disinformation at scale. Detecting such LLM-generated content is crucial, yet current detectors often struggle to generalize in…

The growing number of Internet users and the prevalence of web applications make it necessary to deal with very complex software and applications in the network. This results in an increasing number of new vulnerabilities in the systems,…

Phishing often targets victims through visually perturbed texts to bypass security systems. The noise contained in these texts functions as an adversarial attack, designed to deceive language models and hinder their ability to accurately…

Plagiarism in programming courses remains a persistent challenge, especially in competitive programming contexts where assignments often have unique, known solutions. This paper examines why traditional code plagiarism detection methods…

OpenAI's GPT-Image-2 has effectively erased the visual boundary between authentic and AI-edited document images: a single number on a receipt can be replaced in under a second for a few cents. We release AIForge-Doc v2, a paired dataset of…

LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, but because the skill it invoked broke its own declared safety rules. We call these…

Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show…

AI coding agents are increasingly integrated into real-world software development workflows, yet their robustness under diverse and adversarial scenarios remains poorly understood. We present ABTest, a behavior-driven fuzzing framework that…

In company with the data explosion over the past decade, deep neural network (DNN) based software has experienced unprecedented leap and is becoming the key driving force of many novel industrial applications, including many safety-critical…

Information cocoons on social media limit users' exposure to posts with diverse viewpoints. Modern platforms use stance detection as an important signal in recommendation and ranking pipelines, which can route posts primarily to like-minded…