Tootfinder

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
Jing-Jing Li, Jianfeng He, Chao Shang, Devang Kulshreshtha, Xun Xian, Yi Zhang, Hang Su, Sandesh Swamy, Yanjun Qi
https://arxiv.org/abs/2509.25624

STAC: When Innocent Tools Form Dangerous Chains to Jailbreak LLM Agents
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 multi-turn attack framework that exploits agent tool use. STAC chains together tool calls that each appear harmless in isolation but, when combined, collectively enable harmful operations that only become apparent at the final execution step. We apply our frame…

Google launches the Data Commons MCP Server, allowing developers to integrate its collection of public datasets into AI systems via natural language queries (Jagmeet Singh/TechCrunch)
https://techcrunch.com/2025/09/24/goog

Google makes real-world data more accessible to AI — and training pipelines will love it | TechCrunch
Google’s Data Commons gets an MCP Server to help AI systems access massive amounts of real-world data.

PCCL: Photonic circuit-switched collective communication for distributed ML
Abhishek Vijaya Kumar, Arjun Devraj, Rachee Singh
https://arxiv.org/abs/2509.15450 https://

PCCL: Photonic circuit-switched collective communication for distributed ML
Modern distributed ML suffers from a fundamental gap between the theoretical and realized performance of collective communication algorithms due to congestion and hop-count induced dilation in practical GPU clusters. We present PCCL, a Photonic Collective Communication Library that reconfigures the network topology to match the communication patterns of collective algorithms, thereby eliminating congestion and dilation by creating direct, contention-free circuits between communicating GPUs. Unl…

"Je dis souvent que les économistes sont des sociologues en situation de handicap cognitif, des spécialistes de sociétés qui n’existent pas qui construisent des modèles qui ressemblent plus aux Sims qu’Š la réalité."
translation:
"I often say that economists are sociologists with cognitive disabilities, specialists in societies that do not exist that build models that are more like Sims than reality."
Timothée Parrique Response to Latouche

Personalized Federated Learning with Heat-Kernel Enhanced Tensorized Multi-View Clustering
Kristina P. Sinaga
https://arxiv.org/abs/2509.16101 https://arxi…

Personalized Federated Learning with Heat-Kernel Enhanced Tensorized Multi-View Clustering
We present a robust personalized federated learning framework that leverages heat-kernel enhanced tensorized multi-view fuzzy c-means clustering with advanced tensor decomposition techniques. Our approach integrates heat-kernel coefficients adapted from quantum field theory with Tucker decomposition and canonical polyadic decomposition (CANDECOMP/PARAFAC) to transform conventional distance metrics and efficiently represent high-dimensional multi-view structures. The framework employs matriculat…

Bine Trees: Enhancing Collective Operations by Optimizing Communication Locality
Daniele De Sensi, Saverio Pasqualoni, Lorenzo Piarulli, Tommaso Bonato, Seydou Ba, Matteo Turisini, Jens Domke, Torsten Hoefler
https://arxiv.org/abs/2508.17311

Bine Trees: Enhancing Collective Operations by Optimizing Communication Locality
Communication locality plays a key role in the performance of collective operations on large HPC systems, especially on oversubscribed networks where groups of nodes are fully connected internally but sparsely linked through global connections. We present Bine (binomial negabinary) trees, a family of collective algorithms that improve communication locality. Bine trees maintain the generality of binomial trees and butterflies while cutting global-link traffic by up to 33%. We implement eight Bi…

Asymptotic Scaling Law Analysis of Multicast Satellite Communications with Massive MIMO
Seyong Kim, Jeonghun Park
https://arxiv.org/abs/2509.16921 https://…

Asymptotic Scaling Law Analysis of Multicast Satellite Communications with Massive MIMO
In this paper, we consider a geostationary orbit (GEO) satellite communication system that employs massive multiple-input multiple-output (MIMO) for multicast transmission. By modeling the spatial distribution of ground users using a Poisson point process (PPP) and assuming a fixed-beam precoding is adopted, we find a closed-form expression for the asymptotical rate scaling law as a function of the number of antennas and the scaling factors of user density and multicast users. From the derived …

DiskJoin: Large-scale Vector Similarity Join with SSD
Yanqi Chen, Xiao Yan, Alexandra Meliou, Eric Lo
https://arxiv.org/abs/2508.18494 https://arxiv.org/pd…

DiskJoin: Large-scale Vector Similarity Join with SSD
Similarity join--a widely used operation in data science--finds all pairs of items that have distance smaller than a threshold. Prior work has explored distributed computation methods to scale similarity join to large data volumes but these methods require a cluster deployment, and efficiency suffers from expensive inter-machine communication. On the other hand, disk-based solutions are more cost-effective by using a single machine and storing the large dataset on high-performance external stor…

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs
Vincent Siu, Nicholas Crispino, David Park, Nathan W. Henry, Zhun Wang, Yang Liu, Dawn Song, Chenguang Wang
https://arxiv.org/abs/2509.13450

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs
We introduce SteeringControl, a benchmark for evaluating representation steering methods across core alignment objectives--bias, harmful generation, and hallucination--and their effects on secondary behaviors such as sycophancy and commonsense morality. While prior alignment work often highlights truthfulness or reasoning ability to demonstrate the side effects of representation steering, we find there are many unexplored tradeoffs not yet understood in a systematic way. We collect a dataset of…