Tootfinder

Common Weedkiller Ingredient Harms Gut Bacteria and Multiple Organs: Study #environment

Common Weedkiller Ingredient Harms Gut Bacteria and Multiple Organs: Study
The chemical diquat, used in place of glyphosate in weedkillers in the U.S., has been found to damage organs and kill gut bacteria.

I have no words. Satire is dead.
https://www.theguardian.com/us-news/2025/jun/12/boos-cheers-and-a-heavy-dose-of-irony-as-trump-takes-in-les-mis-against-backdrop-of-la-protests

Ransomware-Verdacht: Französische Polizei verhaftet russischen Basketballer
Laut einem Medienbericht ist ein russischer Basketballspieler auf Antrag der USA in Frankreich festgenommen und inhaftiert worden. Der bestreitet alle Vorwürfe.

A family opened a town's first bookstore. A bathroom bill is driving them away. (Casey Parks/Washington Post)
https://www.washingtonpost.com/nation/2025/08/10/transgender-bathroom-bill-south-dakota-bookstore-family/?pwapi_token=eyJ0eXAiOiJKV1QiLCJhbGciOiJIUzI1NiJ9.eyJyZWFzb24iOiJnaWZ0IiwibmJmIjoxNzU0Nzk4NDAwLCJpc3MiOiJzdWJzY3JpcHRpb25zIiwiZXhwIjoxNzU2MTgwNzk5LCJpYXQiOjE3NTQ3OTg0MDAsImp0aSI6IjAxNmQzNWNkLTJhYzYtNDhiZi1hNzIyLTJmMDQxNWRmNGU5OCIsInVybCI6Imh0dHBzOi8vd3d3Lndhc2hpbmd0b25wb3N0LmNvbS9uYXRpb24vMjAyNS8wOC8xMC90cmFuc2dlbmRlci1iYXRocm9vbS1iaWxsLXNvdXRoLWRha290YS1ib29rc3RvcmUtZmFtaWx5LyJ9.H2Orn-KOHjHp2KVHZgq_x_bOoRNNuilnRl8HjwzgdKs&itid=gfta
http://www.memeorandum.com/250810/p57#a250810p57

Ein Team am Helmholtz-Zentrum für Infektionsforschung entwickelt mit Unterstützung des Deutschen Zentrums für Infektionsforschung ein lebendes #Biotherapeutikum auf Basis von Klebsiella oxytoca, das krankmachende Bakterien wie K. pneumoniae aus dem Darm verdrängen soll.
Ziel ist eine Kapsel mit gefriergetrockneten

Mit der Kraft des Mikrobioms gegen Infektionen
DZIF fördert HZI-Projekt zur Entwicklung eines lebenden Biotherapeutikums. Klebsiella oxytoca verdrängt dabei andere pathogene Bakterien im Darm.

Your Agent Can Defend Itself against Backdoor Attacks
Li Changjiang, Liang Jiacheng, Cao Bochuan, Chen Jinghui, Wang Ting
https://arxiv.org/abs/2506.08336 …

Your Agent Can Defend Itself against Backdoor Attacks
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be manipulated to execute malicious operations when presented with specific triggers in their inputs or environments. To address this pressing risk, we present ReAgent, a novel defense against a range of backdoor attacks on LLM-based agents. Intuitively, backdoor attacks often res…

ESET says a high-severity WinRAR zero-day is being exploited by two Russian cybercrime groups, enabling persistent backdoors when malicious files are opened (Dan Goodin/Ars Technica)
https://arstechnica.com/security/2025/08/high-severity-w…

High-severity WinRAR 0-day exploited for weeks by 2 groups
Exploits allow for persistent backdooring when targets open booby-trapped archive.

KI-Psychose: Warum Chatbots wahnhafte Ideen bestärken können
Ein Chatbot als Spiegel der Seele. Was passiert, wenn dieser Risse bekommt und eine verzerrte Realität zeigt, die für manche zur gefährlichen Gewissheit wird?

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
Zhengxian Wu, Juan Wen, Wanli Peng, Haowei Chang, Yinghan Zhou, Yiming Xue
https://arxiv.org/abs/2508.06153

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
With the development of customized large language model (LLM) agents, a new threat of black-box backdoor attacks has emerged, where malicious instructions are injected into hidden system prompts. These attacks easily bypass existing defenses that rely on white-box access, posing a serious security challenge. To address this, we propose SLIP, a Soft Label mechanism and key-extraction-guided CoT-based defense against Instruction backdoors in APIs. SLIP is designed based on two key insights. First…

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Songze Li, Mingxuan Zhang, Oubo Ma, Kang Wei, Shouling Ji
https://arxiv.org/abs/2506.09562

TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning
Deep reinforcement learning (DRL) has achieved remarkable success in a wide range of sequential decision-making domains, including robotics, healthcare, smart grids, and finance. Recent research demonstrates that attackers can efficiently exploit system vulnerabilities during the training phase to execute backdoor attacks, producing malicious actions when specific trigger patterns are present in the state observations. However, most existing backdoor attacks rely primarily on simplistic and heu…