相关论文: Context-Auditor: Context-sensitive Content Injecti…

As AI agents become more widely deployed, we are likely to see an increasing number of incidents: events involving AI agent use that directly or indirectly cause harm. For example, agents could be prompt-injected to exfiltrate private…

Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, significantly enhancing artistic creation and visual…

With the growing use of information technology in all life domains, hacking has become more negatively effective than ever before. Also with developing technologies, attacks numbers are growing exponentially every few months and become more…

Web applications are becoming an essential part of our everyday lives. Many of our activities are dependent on the functionality and security of these applications. As the scale of these applications grows, injection vulnerabilities such as…

Modern web browsers have effectively become the new operating system for business applications, yet their security posture is often under-scrutinized. This paper presents a novel, comprehensive Browser Security Posture Analysis…

Textual adversarial attacks expose the vulnerabilities of text classifiers and can be used to improve their robustness. Existing context-aware methods solely consider the gold label probability and use the greedy search when searching an…

Judging an action's safety requires knowledge of the context in which the action takes place. To human agents who act in various contexts, this may seem obvious: performing an action such as email deletion may or may not be appropriate…

Due to the fourth industrial revolution, and the resulting increase in interconnectivity, industrial networks are more and more opened to publicly available networks. Apart from the huge benefit in manageability and flexibility, the…

Web agents, powered by large language models (LLMs), are increasingly deployed to automate complex web interactions. The rise of open-source frameworks (e.g., Browser Use, Skyvern-AI) has accelerated adoption, but also broadened the attack…

Intrusion Detection is one of major threats for organization. The approach of intrusion detection using text processing has been one of research interests which is gaining significant importance from researchers. In text mining based…

Prompt injection attacks, where malicious input is designed to manipulate AI systems into ignoring their original instructions and following unauthorized commands instead, were first discovered by Preamble, Inc. in May 2022 and responsibly…

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…

Intrusion Detection System (IDS) is one of the security measures being used as an additional defence mechanism to prevent the security breaches on web. It has been well known methodology for detecting network-based attacks but still…

Black-box adversarial attacks have demonstrated strong potential to compromise machine learning models by iteratively querying the target model or leveraging transferability from a local surrogate model. Recently, such attacks can be…

Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models infer the source of text based on how it sounds, not where it actually comes from. A command…

Many tools and libraries are readily available to build and operate distributed Web applications. While the setup of operational environments is comparatively easy, practice shows that their continuous secure operation is more difficult to…

Cybersecurity education is considered an important part of undergraduate computing curricula, but many institutions teach it only in dedicated courses or tracks. This optionality risks students graduating with limited exposure to secure…

In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker…

Multi-targeted adversarial attacks aim to mislead classifiers toward specific target classes using a single perturbation generator with a conditional input specifying the desired target class. Existing methods face two key limitations: (1)…

Text understanding often suffers from domain shifts. To handle testing domains, domain adaptation (DA) is trained to adapt to a fixed and observed testing domain; a more challenging paradigm, test-time adaptation (TTA), cannot access the…