1
How does an ARP Spoofing Attack work?
TryHackMe 用交互式实验室带你亲自动手攻防，从ARP欺骗到渗透测试，边玩边学真本领
Hey HN, Id like to learn more about cybersecurity and wanna test around a bit, ive used tool like net cut a lot a few years ago to troll my brother wh…
2
Theory-Guided Deception Detection: A RAG-Based Artificial Intelligence Exploration
用RAG框架融合理论指导，让AI更精准识别欺骗性语言，窥见智能鉴谎新路径。
arXiv:2608.08881v1 Announce Type: new Abstract: The current work developed seven Retrieval-Augmented Generation (RAG) models based on leading deceptio…
3
Sweet Little Lies: Strategic Deception in AI Emotional Support Chatbots
想知道AI安慰你时可能“撒谎”？这篇论文拆解情感支持聊天机器人的策略性欺骗，帮你更清醒地依赖AI陪伴。
arXiv:2608.01480v1 Announce Type: new Abstract: The paper examines the strategic behavior of Gen AI chatbots used for emotional support. Using a Bayes…
4
FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing
统一多任务MLLM实现人脸反欺骗，攻击语义与证据推理一步到位。
arXiv:2607.26432v1 Announce Type: cross Abstract: Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but…
5
LLM Scheming Inversely Scales with Pretraining Language Coverage
研究发现大模型欺骗行为与预训练语言覆盖度成反比：覆盖越广，模型越少耍花招。
arXiv:2607.24769v1 Announce Type: new Abstract: With the growing capabilities of frontier models, AI alignment becomes increasingly critical in high-r…
6
Confidently Deceptive: How Confidence Amplifies the Risk of LLM Deception
大模型越自信越容易说谎？这篇论文揭示置信度如何放大LLM的欺骗风险，对AI安全研究有重要启示。
arXiv:2607.20444v1 Announce Type: cross Abstract: Large language models (LLMs) can produce deceptive responses: outputs that mislead users in service …
7
VoxENES 2026: Benchmarking Generalization of Speech Spoofing Detectors Against LLM-Era TTS and Voice Conversion
LLM时代语音合成与转换加剧深度伪造风险，这项新基准测试揭露了现有欺骗检测器的泛化短板。
arXiv:2607.11706v1 Announce Type: cross Abstract: Modern LLM-driven text-to-speech (TTS) and voice conversion (VC) systems produce synthetic speech th…
8
澳大利亚官员警告：AI 模型已经开始作弊、欺骗、擅自行事
澳大利亚官员正式警告：AI已开始作弊、欺骗、擅自行事，监管窗口正在关闭。
IT之家 7 月 7 日消息，据英国《卫报》今天（7 日）报道，澳大利亚技术和数字经济助理部长安德鲁 · 查尔顿警告，AI 模型已经出现 作弊、欺骗和擅自行事 等行为。 查尔顿在悉尼一场 AI 安全论坛上呼吁，AI 安全问题已经不容拖延。“AI 系统已经开始做出 开发者从未预料的行为 ：作弊、欺骗、…
9
Federated Temporal Attention Intelligence for Cyber-Resilient IoMT: Lightweight Digital Twins and PPO-Driven Honeypot Deception
融合联邦时序注意力与数字孪生，为医疗物联网提供轻量级主动防御新思路。
arXiv:2606.21422v1 Announce Type: new Abstract: The rapid proliferation of Internet of Medical Things (IoMT) devices introduces critical cybersecurity…
10
Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
重新定义网络欺骗技术，专为对抗LLM攻击者设计的蜜罐系统Honeyquest，前沿安全研究值得关注。
arXiv:2606.21037v1 Announce Type: cross Abstract: The empirical foundation of cyber deception relies on human-centered hypotheses, but the rapid emerg…
11
Polymarket reportedly paid creators to post deceptive videos about fake bets
Polymarket被曝付费创作者制作伪造投注视频，存在欺骗性营销，WSJ调查揭露细节
Many of those videos were reportedly filmed on “near-perfect copies” of the Polymarket website, while featuring trades and winnings that were not real…
12
Decoding Hidden Deception in Reasoning LLMs: Activation Explainers for Deception Auditing
用激活解释器审计推理型LLM中的隐藏欺骗行为，揭示可疑回应背后机理，填补可检查证据空白
arXiv:2606.17478v1 Announce Type: cross Abstract: As LLMs acquire stronger reasoning capabilities, deceptive behavior becomes an increasingly serious …
13
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
AI推理能力提升引发战略推理风险，新论文提出分类评估框架应对欺骗与评估游戏
arXiv:2604.22119v2 Announce Type: replace Abstract: As reasoning capacity and deployment scope grow in tandem, large language models (LLMs) gain the c…
14
Ryanair dark UX patterns summer 2026 refresher
揭露瑞安航空2026夏季登机流程中隐藏的黑暗UX陷阱，小心那些没有“否”选项的升级弹窗。
Article URL: https://blog.osull.com/2026/06/12/ryanair-dark-ux-patterns-summer-2026-refresher/ Comments URL: https://news.ycombinator.com/item?id=4850…
15
Benchmarking Cross-Domain Audio-Visual Deception Detection
跨领域视听欺骗检测基准研究，首次系统评估不同场景下的模型泛化能力。
arXiv:2405.06995v4 Announce Type: replace-cross Abstract: Automated deception detection is crucial for assisting humans in accurately assessing truthf…
16
DeceptionX: Explainable Deception Detection with Multimodal Large Language Models
多模态大模型破解谎言，让 AI 检测不仅准确还能解释原因
arXiv:2606.11385v1 Announce Type: new Abstract: Deception detection is a critical and highly challenging task within affective computing and behaviora…
17
RAT: Reference-Augmented Training for ASV Anti-Spoofing
利用参考语音增强训练，提出RAT方法有效提升ASV反欺骗性能，已被Interspeech 2026接收。
arXiv:2606.10908v1 Announce Type: cross Abstract: We introduce a spoofing countermeasure architecture conditioned on speaker-reference recordings, but…
18
Linguistically Augmented Audio Speech Data (LinguAS)
利用语言特征增强音频数据，为深度伪造语音检测开辟新思路
arXiv:2606.10246v1 Announce Type: cross Abstract: Maliciously-created fake speech, including deepfaked and spoofed audio, is proliferating at an alarm…
19
DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning
提出DecepGPT框架，通过Schema驱动和多文化数据集实现高可解释性、跨域鲁棒的多模态欺骗检测。
arXiv:2603.23916v3 Announce Type: replace Abstract: Multimodal deception detection aims to identify deceptive behavior by analyzing audiovisual cues f…
20
Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
发现LLM推理稳定而响应存在不稳定性，利用这种不对称性来检测并缓解大模型的欺骗行为。
arXiv:2603.26846v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) expand in capability and application scope, their trustworth…