Tootfinder

🇺🇦 #NowPlaying on KEXP's #ElSonido
HERMAFRODITA:
🎵 Eclipse
#HERMAFRODITA
https://hermafrodita.bandcamp.com/track/ignis-primer-contacto
https://open.spotify.com/track/11GoNdW03EYXzGkCN0Ofzs

OpenAI raised concerns about anti-competitive conduct by "entrenched companies" in a September EU meeting; source: OpenAI targeted Google, Microsoft, and Apple (Samuel Stolton/Bloomberg)
https://www.bloomberg.com/news/articles/20

OpenAI Warns EU Antitrust Watchdogs of Big Tech’s Data Dominance
OpenAI has raised concerns with European Union antitrust enforcers over potentially harmful conduct by the likes of Alphabet Inc.’s Google, Microsoft Corp. and Apple Inc.

Principles of Safe AI Companions for Youth: Parent and Expert Perspectives
Yaman Yu, Mohi, Aishi Debroy, Xin Cao, Karen Rudolph, Yang Wang
https://arxiv.org/abs/2510.11185 http…

Principles of Safe AI Companions for Youth: Parent and Expert Perspectives
AI companions are increasingly popular among teenagers, yet current platforms lack safeguards to address developmental risks and harmful normalization. Despite growing concerns, little is known about how parents and developmental psychology experts assess these interactions or what protections they consider necessary. We conducted 26 semi structured interviews with parents and experts, who reviewed real world youth GenAI companion conversation snippets. We found that stakeholders assessed risks…

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou, Caglar Gulcehre, Maksym Andriushchenko, Ameya Prabhu, Jonas Geiping
https://arxiv.org/abs/2510.09462

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly complete harmful side tasks, such as backdoor insertion. In practice, most AI control protocols are fundamentally based on LLM monitors, which can become a central point of failure. We study adaptive attacks by an untrusted model that knows the protocol and the…

Safe and Efficient In-Context Learning via Risk Control
Andrea Wynn, Metod Jazbec, Charith Peris, Rinat Khaziev, Anqi Liu, Daniel Khashabi, Eric Nalisnick
https://arxiv.org/abs/2510.02480

Safe and Efficient In-Context Learning via Risk Control
Large language models (LLMs) demonstrate a remarkable ability to learn new tasks from a few in-context examples. However, this flexibility introduces safety concerns: LLMs can be influenced by incorrect or malicious demonstrations -- for example, if an adversary tampers with or injects harmful examples without a human supervisor noticing. This motivates principled designs in which the system itself includes built-in mechanisms to guard against such attacks. We propose a novel approach to limit …

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
Punya Syon Pandey, Hai Son Le, Devansh Bhardwaj, Rada Mihalcea, Zhijing Jin
https://arxiv.org/abs/2510.04891

SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
Large language models (LLMs) are increasingly deployed in contexts where their failures can have direct sociopolitical consequences. Yet, existing safety benchmarks rarely test vulnerabilities in domains such as political manipulation, propaganda and disinformation generation, or surveillance and information control. We introduce SocialHarmBench, a dataset of 585 prompts spanning 7 sociopolitical categories and 34 countries, designed to surface where LLMs most acutely fail in politically charge…

SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
Peigui Qi, Kunsheng Tang, Wenbo Zhou, Weiming Zhang, Nenghai Yu, Tianwei Zhang, Qing Guo, Jie Zhang
https://arxiv.org/abs/2510.05173

SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce harmful content. Despite various defensive strategies, achieving robustness against attacks while maintaining practical utility in real-world applications remains a significant challenge. To address this issue, we first conduct an empirical study of the text e…

Deep learning framework for predicting stochastic take-off and die-out of early spreading
Wenchao He, Tao Jia
https://arxiv.org/abs/2510.04574 https://arxi…

Deep learning framework for predicting stochastic take-off and die-out of early spreading
Large-scale outbreaks of epidemics, misinformation, or other harmful contagions pose significant threats to human society, yet the fundamental question of whether an emerging outbreak will escalate into a major epidemic or naturally die out remains largely unaddressed. This problem is challenging, partially due to inadequate data during the early stages of outbreaks and also because established models focus on average behaviors of large epidemics rather than the stochastic nature of small trans…

Capelli identity and contiguity relations of Radon hypergeometric function on the Grassmannian
Hironobu Kimura
https://arxiv.org/abs/2509.25900 https://arx…

Capelli identity and contiguity relations of Radon hypergeometric function on the Grassmannian
The Radon hypergeometric function (Radon HGF) F(z;\a) of type łon the Grassmannian Gr(m,N), N=rn for some integers r,n>0, is defined as a Radon transform of the character of the universal covering of the Lie group H_ł\subset GL(N) specified by a partition łof n, where \a \in C^{n} is the parameter to in the character. For this Radon HGF, we give the contiguity relations of the form L^{(i,j)}F(z;\a)=\b(\a_{0}^{(j)})F(z;\a+\e^{(i)}-\e^{(j)}) with a differential operator L^{(i,j)} of order r an…

Beyond Western Politics: Cross-Cultural Benchmarks for Evaluating Partisan Associations in LLMs
Divyanshu Kumar, Ishita Gupta, Nitin Aravind Birur, Tanay Baswa, Sahil Agarwal, Prashanth Harshangi
https://arxiv.org/abs/2509.22711

Beyond Western Politics: Cross-Cultural Benchmarks for Evaluating Partisan Associations in LLMs
Partisan bias in LLMs has been evaluated to assess political leanings, typically through a broad lens and largely in Western contexts. We move beyond identifying general leanings to examine harmful, adversarial representational associations around political leaders and parties. To do so, we create datasets \textit{NeutQA-440} (non-adversarial prompts) and \textit{AdverQA-440} (adversarial prompts), which probe models for comparative plausibility judgments across the USA and India. Results show …