Tootfinder

Rejoignez notre mission en faisant un don chaque mois. Avec 585 personnes donnant €10/mois ou 117 personnes offrant €50/mois, nous atteindrons nos objectifs! Ensemble, amplifions les voix des victimes! Partagez cet appel avec votre entourage. 🙏🏽💙 https://chardonsbleus.org/cagnotte-en-ligne

Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
Xikang Yang, Biyu Zhou, Xuehai Tang, Jizhong Han, Songlin Hu
https://arxiv.org/abs/2507.22564 https://

Exploiting Synergistic Cognitive Biases to Bypass Safety in LLMs
Large Language Models (LLMs) demonstrate impressive capabilities across a wide range of tasks, yet their safety mechanisms remain susceptible to adversarial attacks that exploit cognitive biases -- systematic deviations from rational judgment. Unlike prior jailbreaking approaches focused on prompt engineering or algorithmic manipulation, this work highlights the overlooked power of multi-bias interactions in undermining LLM safeguards. We propose CognitiveAttack, a novel red-teaming framework t…

Building Trustworthy Cognitive Monitoring for Safety-Critical Human Tasks: A Phased Methodological Approach
Maciej Grzeszczuk, Grzegorz Pochwatko, Barbara Karpowicz, Stanis{\l}aw Knapi\'nski, Wies{\l}aw Kope\'c
https://arxiv.org/abs/2506.22066

Building Trustworthy Cognitive Monitoring for Safety-Critical Human Tasks: A Phased Methodological Approach
Operators performing high-stakes, safety-critical tasks - such as air traffic controllers, surgeons, or mission control personnel - must maintain exceptional cognitive performance under variable and often stressful conditions. This paper presents a phased methodological approach to building cognitive monitoring systems for such environments. By integrating insights from human factors research, simulation-based training, sensor technologies, and fundamental psychological principles, the proposed…

Verification Cost Asymmetry in Cognitive Warfare: A Complexity-Theoretic Framework
Joshua Luberisse
https://arxiv.org/abs/2507.21258 https://arxiv.org/pdf/…

Verification Cost Asymmetry in Cognitive Warfare: A Complexity-Theoretic Framework
Human verification under adversarial information flow operates as a cost-bounded decision procedure constrained by working memory limits and cognitive biases. We introduce the Verification Cost Asymmetry (VCA) coefficient, formalizing it as the ratio of expected verification work between populations under identical claim distributions. Drawing on probabilistically checkable proofs (PCP) and parameterized complexity theory, we construct dissemination protocols that reduce verification for truste…

Un grand merci aux 148 donateur-ices généreux qui ont contribué Š notre cagnotte ! Ensemble, nous progressons vers notre but de récolter 12439 €. Votre soutien est inestimable ! 🙏
https://chardonsbleus.org/cagnotte-en-ligne/

This https://arxiv.org/abs/2505.17418 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csHC_…

What Needs Attention? Prioritizing Drivers of Developers' Trust and Adoption of Generative AI
Generative AI (genAI) tools are advertised as productivity aids. Yet, issues related to miscalibrated trust and usage friction continue to hinder their adoption. Additionally, AI can be exclusionary, failing to support diverse users adequately, further exacerbating these concerns. One such aspect of diversity is cognitive diversity -- variations in users' cognitive styles -- that leads to divergence in interaction styles. When an individual's cognitive styles are unsupported, it creates additio…

🌟 Soutenons les 6 survivant-es dans l’affaire OKC-Spatz pour qu'ils obtiennent justice ! 🙏 L'instruction touche Š sa fin, participons Š la cagnotte pour les aider financièrement. 💙 Découvrez comment contribuer ici : 👉 https://chardonsbleus.org/cagnotte-en-ligne

⚖️ Justice pour les victimes de dérives sectaires. L’affaire OKC-Spatz doit passer au procès, mais l’accès Š la justice reste un luxe. Ensemble, faisons bouger les lignes. 💙 👉 https://chardonsbleus.org/cagnotte-en-ligne

🌟 Un grand merci Š chacun de vous ! 🌟
Grâce Š votre incroyable soutien, nous avons déjŠ collecté 4889 € pour aider les victimes et progresser vers la justice. 🙏 https://chardonsbleus.org/cagnotte-en-ligne/
1/4

Notre objectif : 12 439 € ! 💼 Grâce Š votre générosité, nous avons déjŠ atteint les 5134 €. Pour aller plus loin, nous comptons sur vous. Chaque contribution compte. Merci ! 🙏 👉 https://chardonsbleus.org/cagnotte-en-ligne