中文
相关论文

相关论文: Synthetic Trust Attacks: Modeling How Generative A…

200 篇论文

As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns. This paper introduces Sequential Tool Attack Chaining (STAC), a novel…

密码学与安全 · 计算机科学 2026-02-03 Jing-Jing Li , Jianfeng He , Chao Shang , Devang Kulshreshtha , Xun Xian , Yi Zhang , Hang Su , Sandesh Swamy , Yanjun Qi

Recent proposals advocate using keystroke timing signals, specifically the coefficient of variation ($\delta$) of inter-keystroke intervals, to distinguish human-composed text from AI-generated content. We demonstrate that this class of…

密码学与安全 · 计算机科学 2026-01-27 David Condrey

Enabling large language models (LLMs) to solve complex reasoning tasks is a key step toward artificial general intelligence. Recent work augments LLMs with external tools to enable agentic reasoning, achieving high utility and efficiency in…

计算机视觉与模式识别 · 计算机科学 2026-01-27 Qi Li , Xinchao Wang

Fraudulent activities are rapidly evolving, employing increasingly diverse and sophisticated methods that pose serious threats to individuals, organizations, and society. This paper proposes the FIST Framework (Fraud Incident Structured…

密码学与安全 · 计算机科学 2025-06-09 Yu-Chen Dai , Lu-An Chen , Sy-Jye Her , Yu-Xian Jiang

Most adversarial threats in artificial intelligence (AI) target the computational behavior of models rather than the humans who rely on them. Yet modern AI systems increasingly operate within human decision loops, where users interpret and…

人工智能 · 计算机科学 2026-05-18 Shutong Fan , Lan Zhang , Xiaoyong Yuan

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…

人工智能 · 计算机科学 2026-05-07 Chenglin Yang

Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…

密码学与安全 · 计算机科学 2026-05-19 Tsafac Nkombong Regine Cyrille , Franziska Schwarz

Generative AI (GenAI) now produces text, images, audio, and video that can be perceptually convincing at scale and at negligible marginal cost. While public debate often frames the associated harms as "deepfakes" or incremental extensions…

计算机与社会 · 计算机科学 2026-01-05 Emilio Ferrara

Large Reasoning Models (LRMs) and Multi-Agent Systems (MAS) in high-stakes domains demand reliable verification, yet centralized approaches suffer four limitations: (1) Robustness, with single points of failure vulnerable to attacks and…

人工智能 · 计算机科学 2026-05-01 Yu-Chao Huang , Zhen Tan , Mohan Zhang , Pingzhi Li , Zhuo Zhang , Tianlong Chen

Large language model (LLM) agents are rapidly becoming trusted copilots in high-stakes domains like software development and healthcare. However, this deepening trust introduces a novel attack surface: Agent-Mediated Deception (AMD), where…

人机交互 · 计算机科学 2026-02-25 Xinfeng Li , Shenyu Dai , Kelong Zheng , Yue Xiao , Gelei Deng , Wei Dong , Xiaofeng Wang

Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks, which brings a huge security risk to the further application of DNNs, especially for the AI models developed in the real world.…

计算机视觉与模式识别 · 计算机科学 2023-12-13 Renyang Liu , Wei Zhou , Sixin Wu , Jun Zhao , Kwok-Yan Lam

In a world where deepfakes and cloned voices are emerging as sophisticated attack vectors, organizations require a new security mindset: Sensorial Zero Trust [9]. This article presents a scientific analysis of the need to systematically…

密码学与安全 · 计算机科学 2025-07-02 Fabio Correa Xavier

Large Language Models and commercial speech synthesis systems now enable highly realistic AI-generated voice scams (vishing), raising urgent concerns about deception at scale. Yet it remains unclear whether individuals can reliably…

密码学与安全 · 计算机科学 2026-03-27 Zoha Hayat Bhatti , Bakhtawar Ahtisham , Seemal Tausif , Niklas George , Nida ul Habib Bajwa , Mobin Javed

For decades, the security of digital interaction has rested on an unacknowledged economic constraint. Attackers faced a tradeoff between the fidelity of a deception and the scale at which it could be deployed. Convincing impersonation…

密码学与安全 · 计算机科学 2026-05-19 Osama Zafar , Alexander Nemecek , Erman Ayday

The CIA security triad - Confidentiality, Integrity, and Availability - is a cornerstone of data and cybersecurity. With the emergence of large language model (LLM) applications, a new class of threat, known as prompt injection, was first…

密码学与安全 · 计算机科学 2024-12-10 Johann Rehberger

Despite the importance of developing generative AI models that can effectively resist scams, current literature lacks a structured framework for evaluating their vulnerability to such threats. In this work, we address this gap by…

密码学与安全 · 计算机科学 2025-07-18 Udari Madhushani Sehwag , Kelly Patel , Francesca Mosca , Vineeth Ravi , Jessica Staddon

Symbolic analysis of security exploits in smart contracts has demonstrated to be valuable for analyzing predefined vulnerability properties. While some symbolic tools perform complex analysis steps, they require a predetermined invocation…

密码学与安全 · 计算机科学 2019-06-10 Wesley Joon-Wie Tann , Xing Jie Han , Sourav Sen Gupta , Yew-Soon Ong

In an era where digital threats are increasingly sophisticated, the intersection of Artificial Intelligence and cybersecurity presents both promising defenses and potent dangers. This paper delves into the escalating threat posed by the…

密码学与安全 · 计算机科学 2024-08-26 Yusuf Usman , Aadesh Upadhyay , Prashnna Gyawali , Robin Chataut

Zero Trust Architectures (ZTA) fundamentally redefine network security by adopting a "trust nothing, verify everything" approach that requires identity verification for all access. Conventional discrete access control measures have proven…

密码学与安全 · 计算机科学 2025-01-14 Sina Ahmadi

Alignment faking (AF) occurs when an LLM strategically complies with training objectives to avoid value modification, reverting to prior preferences once monitoring is lifted. Current detection methods focus on conversational settings and…

密码学与安全 · 计算机科学 2026-04-30 Matteo Leonesi , Francesco Belardinelli , Flavio Corradini , Marco Piangerelli
‹ 上一页 1 2 3 10 下一页 ›