Tootfinder

PromptLocate: Localizing Prompt Injection Attacks
Yuqi Jia, Yupei Liu, Zedian Shao, Jinyuan Jia, Neil Gong
https://arxiv.org/abs/2510.12252 https://arxiv.o…

PromptLocate: Localizing Prompt Injection Attacks
Prompt injection attacks deceive a large language model into completing an attacker-specified task instead of its intended task by contaminating its input data with an injected prompt, which consists of injected instruction(s) and data. Localizing the injected prompt within contaminated data is crucial for post-attack forensic analysis and data recovery. Despite its growing importance, prompt injection localization remains largely unexplored. In this work, we bridge this gap by proposing Prompt…

Extended Version: It Should Be Easy but... New Users Experiences and Challenges with Secret Management Tools
Lorenzo Neil, Deepthi Mungara, Laurie Williams, Yasemin Acar, Bradley Reaves
https://arxiv.org/abs/2509.09036

Extended Version: It Should Be Easy but... New Users Experiences and Challenges with Secret Management Tools
Software developers face risks of leaking their software secrets, such as API keys or passwords, which can result in significant harm. Secret management tools (SMTs), such as HashiCorp Vault Secrets or Infisical, are highly recommended by industry, academia, and security guidelines to manage secrets securely. SMTs are designed to help developers secure their secrets in a central location, yet secrets leaks are still commonplace, and developers report difficulty in learning how to setup and use …

Fixed points of classical gravity coupled with a Standard-Model-like theory
Latham Boyle, Neil Turok, Vatsalya Vaibhav
https://arxiv.org/abs/2509.09346 https://

Fixed points of classical gravity coupled with a Standard-Model-like theory
Coupling quantum field theory (QFT) \!-\! even free QFT \!-\! to gravity leads to well-known problems. In particular, the stress tensor $T_{μν}$ (gravity's source) and its correlators typically diverge in the UV, creating a conflict between the wildly inhomogeneous spacetime we expect quantum mechanically and the weakly-curved, macroscopic spacetime we observe. Are there QFTs for which these divergences cancel? Here, for simplicity, we consider free quantum fields on a classical curved backgr…

BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing
Caelin Kaplan, Alexander Warnecke, Neil Archibald
https://arxiv.org/abs/2510.11823 https://

BlackIce: A Containerized Red Teaming Toolkit for AI Security Testing
AI models are being increasingly integrated into real-world systems, raising significant concerns about their safety and security. Consequently, AI red teaming has become essential for organizations to proactively identify and address vulnerabilities before they can be exploited by adversaries. While numerous AI red teaming tools currently exist, practitioners face challenges in selecting the most appropriate tools from a rapidly expanding landscape, as well as managing complex and frequently c…

Risk-based framework to determine climate-informed design storms for road drainage infrastructure
Mohammad Fereshtehpour, Rashid Bashir, Neil F. Tandon
https://arxiv.org/abs/2508.10183

Risk-based framework to determine climate-informed design storms for road drainage infrastructure
Climate change is amplifying extreme precipitation events in many regions and imposes substantial challenges for the resilience of road drainage infrastructure. Conventional design storm methodologies, which rely on historical trends of rainfall data under a stationarity assumption, may not adequately account for future climate variability. This study introduces a risk-based framework for determining climate-informed design storms tailored to road drainage systems. The proposed framework integr…

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
Nevan Wichers, Aram Ebtekar, Ariana Azarbal, Victor Gillioz, Christine Ye, Emil Ryd, Neil Rathi, Henry Sleight, Alex Mallen, Fabien Roger, Samuel Marks
https://arxiv.org/abs/2510.05024

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment
Large language models are sometimes trained with imperfect oversight signals, leading to undesired behaviors such as reward hacking and sycophancy. Improving oversight quality can be expensive or infeasible, motivating methods that improve learned behavior despite an imperfect training signal. We introduce Inoculation Prompting (IP), a simple but counterintuitive technique that prevents learning of an undesired behavior by modifying training prompts to explicitly request it. For example, to ino…

Mitigating Modal Imbalance in Multimodal Reasoning
Chen Henry Wu, Neil Kale, Aditi Raghunathan
https://arxiv.org/abs/2510.02608 https://arxiv.org/pdf/2510.…

Mitigating Modal Imbalance in Multimodal Reasoning
Foundation models (FMs) deployed in real-world tasks such as computer-use agents must integrate diverse modalities. How good are FMs at performing joint reasoning, simultaneously reasoning over multiple modalities, especially when the modalities interact and relate to each other to form cross-modal context? To better understand this problem, we study FMs on cross-modal conflicts: scenarios where conflicting evidence is presented across modalities. This allows us to examine whether FMs prioritiz…

Progress and new challenges in image-based profiling
Erik Serrano, John Peters, Jesko Wagner, Rebecca E. Graham, Zhenghao Chen, Brian Feng, Gisele Miranda, Alexandr A. Kalinin, Loan Vulliard, Jenna Tomkinson, Cameron Mattson, Michael J. Lippincott, Ziqi Kang, Divya Sitani, Dave Bunten, Srijit Seal, Neil O. Carragher, Anne E. Carpenter, Shantanu Singh, Paula A. Marin Zapata, Juan C. Caicedo, Gregory P. Way

Progress and new challenges in image-based profiling
For over two decades, image-based profiling has revolutionized cellular phenotype analysis. Image-based profiling processes rich, high-throughput, microscopy data into unbiased measurements that reveal phenotypic patterns powerful for drug discovery, functional genomics, and cell state classification. Here, we review the evolving computational landscape of image-based profiling, detailing current procedures, discussing limitations, and highlighting future development directions. Deep learning h…

Optical Design Pathways to Fluidic Space-Assembled Reflectors & Dual-Configuration Spectrographs for Characterizing Exo-Earths
Enrico Biancalani, Edward Balaban, Ruslan Belikov, Eduardo Bendek, Valeri Frumkin, Israel Gabay, Guangjun Gao, Qian Gong, Christine Gregg, Tyler Groff, Joseph Howard, Omer Luria, Michael McElwain, Lee Mundy, Rachel Ticknor, Sylvain Veilleux, Neil Zimmerman

Optical Design Pathways to Fluidic Space-Assembled Reflectors & Dual-Configuration Spectrographs for Characterizing Exo-Earths
$\textbf{Fluidic Telescopes}$ | We present a conceptual framework for optically designing space-assembled telescopes whose primary mirror is formed $\textit{in situ}$ via the enabling, scale-invariant technology of fluidic shaping. In-space assembly of optical reflectors can solve light-gathering aperture scaling, which currently limits space-borne optical telescopes. Our compass reduces the top-level optical design trade to three types of avenues -- a fluidic pathway, a legacy one buildin…

Quantising Chiral Bosons On Riemann Surfaces
Chris Hull, Neil Lambert
https://arxiv.org/abs/2508.02865 https://arxiv.org/pdf/2508.02865

Quantising Chiral Bosons On Riemann Surfaces
Sen's action in two dimensions governs a chiral boson coupled to a two-dimensional metric together with a second chiral boson that couples to a flat two-dimensional metric. This second scalar decouples from the physical degrees of freedom. The generalisation of this action to one in which the second chiral scalar couples to an arbitrary second metric is used to formulate the theory on an arbitrary two-dimensional manifold. We use this action with both metrics Riemannian (or complex) to formulat…

The two conduction bands of monolayer CrSBr on Au
Yogal Prasad Ghimirey, Laxman Nagireddy, Cephise Cacho, Neil R. Wilson, Matthew D. Watson
https://arxiv.org/abs/2510.04925 http…

The two conduction bands of monolayer CrSBr on Au
We report the electronic structure of monolayer CrSBr exfoliated onto mica template-stripped gold substrates. Angle-resolved photoemission spectroscopy reveals charge transfer from the substrate, populating the conduction band of monolayer CrSBr, accompanied by a pronounced reduction in the quasiparticle band gap. Furthermore, we observe two separate conduction bands that exhibit a splitting at the X point. This indicates a breaking of glide-mirror symmetry, which in the bulk or in a free-stand…

Replaced article(s) found for econ.EM. https://arxiv.org/list/econ.EM/new
[1/1]:
- Counting Defiers: A Design-Based Model of an Experiment Can Reveal Evidence Beyond the Average Ef...
Neil Christy, Amanda Ellen Kowalski

RangeSAM: Leveraging Visual Foundation Models for Range-View repesented LiDAR segmentation
Paul Julius K\"uhn, Duc Anh Nguyen, Arjan Kuijper, Holger Graf, Dieter Fellner, Saptarshi Neil Sinha
https://arxiv.org/abs/2509.15886

RangeSAM: Leveraging Visual Foundation Models for Range-View repesented LiDAR segmentation
Point cloud segmentation is central to autonomous driving and 3D scene understanding. While voxel- and point-based methods dominate recent research due to their compatibility with deep architectures and ability to capture fine-grained geometry, they often incur high computational cost, irregular memory access, and limited real-time efficiency. In contrast, range-view methods, though relatively underexplored - can leverage mature 2D semantic segmentation techniques for fast and accurate predicti…

Accelerating Deterministic Global Optimization via GPU-parallel Interval Arithmetic
Hongzhen Zhang (Department of Chemical Engineering, KU Leuven, Leuven, Belgium), Tim Kerkenhoff (Institute of Climate and Energy Systems - Energy Systems Engineering), Neil Kichler (Software and Tools for Computational Engineering), Manuel Dahmen (Institute of Climate and Energy Systems - Energy Systems Engineering), Alexander Mitsos (JARA-CSD, Aachen, Germany, Process Systems Enginering, Institute of C…

Accelerating Deterministic Global Optimization via GPU-parallel Interval Arithmetic
Spatial Branch and Bound (B&B) algorithms are widely used for solving nonconvex problems to global optimality, yet they remain computationally expensive. Though some works have been carried out to speed up B&B via CPU parallelization, GPU parallelization is much less explored. In this work, we investigate the design of a spatial B&B algorithm that involves an interval-based GPU-parallel lower bounding solver: The domain of each B&B node is temporarily partitioned into numerous subdomains, then …

Evaluation Guidelines for Empirical Studies in Software Engineering involving LLMs
Sebastian Baltes, Florian Angermeir, Chetan Arora, Marvin Mu\~noz Bar\'on, Chunyang Chen, Lukas B\"ohme, Fabio Calefato, Neil Ernst, Davide Falessi, Brian Fitzgerald, Davide Fucci, Marcos Kalinowski, Stefano Lambiase, Daniel Russo, Mircea Lungu, Lutz Prechelt, Paul Ralph, Christoph Treude, Stefan Wagner

Evaluation Guidelines for Empirical Studies in Software Engineering involving LLMs
Large language models (LLMs) are increasingly being integrated into software engineering (SE) research and practice, yet their non-determinism, opaque training data, and evolving architectures complicate the reproduction and replication of empirical studies. We present a community effort to scope this space, introducing a taxonomy of LLM-based study types together with eight guidelines for designing and reporting empirical studies involving LLMs. The guidelines present essential (must) criteria…

Crosslisted article(s) found for cs.MA. https://arxiv.org/list/cs.MA/new
[1/1]:
- ORCA: Agentic Reasoning For Hallucination and Adversarial Robustness in Vision-Language Models
Chung-En Johnny Yu (Neil), Hsuan-Chih (Neil), Chen, Brian Jalaian, Nathaniel D. Bastian