Tootfinder

Learning to Generate Object Interactions with Physics-Guided Video Diffusion
David Romero, Ariana Bermudez, Hao Li, Fabio Pizzati, Ivan Laptev
https://arxiv.org/abs/2510.02284 h…

Learning to Generate Object Interactions with Physics-Guided Video Diffusion
Recent models for video generation have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond their creative potential, such models also hold promise as world simulators for robotics and embodied decision making. Despite strong advances, however, current approaches still struggle to generate physically plausible object interactions and lack physics-grounded control mechanisms. To address this limitation, we introduce KineMask, an approach fo…

Adversarial Decision-Making in Partially Observable Multi-Agent Systems: A Sequential Hypothesis Testing Approach
Haosheng Zhou, Daniel Ralston, Xu Yang, Ruimeng Hu
https://arxiv.org/abs/2509.03727

Adversarial Decision-Making in Partially Observable Multi-Agent Systems: A Sequential Hypothesis Testing Approach
Adversarial decision-making in partially observable multi-agent systems requires sophisticated strategies for both deception and counter-deception. This paper presents a sequential hypothesis testing (SHT)-driven framework that captures the interplay between strategic misdirection and inference in adversarial environments. We formulate this interaction as a partially observable Stackelberg game, where a follower agent (blue team) seeks to fulfill its primary task while actively misleading an ad…

LLMHoney: A Real-Time SSH Honeypot with Large Language Model-Driven Dynamic Response Generation
Pranjay Malhotra
https://arxiv.org/abs/2509.01463 https://a…

LLMHoney: A Real-Time SSH Honeypot with Large Language Model-Driven Dynamic Response Generation
Cybersecurity honeypots are deception tools for engaging attackers and gather intelligence, but traditional low or medium-interaction honeypots often rely on static, pre-scripted interactions that can be easily identified by skilled adversaries. This Report presents LLMHoney, an SSH honeypot that leverages Large Language Models (LLMs) to generate realistic, dynamic command outputs in real time. LLMHoney integrates a dictionary-based virtual file system to handle common commands with low latency…

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain
Shakiba Amirshahi, Amin Bigdeli, Charles L. A. Clarke, Amira Ghenai
https://arxiv.org/abs/2509.03787

Evaluating the Robustness of Retrieval-Augmented Generation to Adversarial Evidence in the Health Domain
Retrieval augmented generation (RAG) systems provide a method for factually grounding the responses of a Large Language Model (LLM) by providing retrieved evidence, or context, as support. Guided by this context, RAG systems can reduce hallucinations and expand the ability of LLMs to accurately answer questions outside the scope of their training data. Unfortunately, this design introduces a critical vulnerability: LLMs may absorb and reproduce misinformation present in retrieved evidence. This…

Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
Oskar Kviman, Kirill Tamogashev, Nicola Branchini, V\'ictor Elvira, Jens Lagergren, Nikolay Malkin
https://arxiv.org/abs/2510.01159

Multi-Marginal Flow Matching with Adversarially Learnt Interpolants
Learning the dynamics of a process given sampled observations at several time points is an important but difficult task in many scientific applications. When no ground-truth trajectories are available, but one has only snapshots of data taken at discrete time steps, the problem of modelling the dynamics, and thus inferring the underlying trajectories, can be solved by multi-marginal generalisations of flow matching algorithms. This paper proposes a novel flow matching method that overcomes the …

Computational Monogamy of Entanglement and Non-Interactive Quantum Key Distribution
Alex B. Grilo, Giulio Malavolta, Michael Walter, Tianwei Zhang
https://arxiv.org/abs/2510.00791

Computational Monogamy of Entanglement and Non-Interactive Quantum Key Distribution
Quantum key distribution (QKD) enables Alice and Bob to exchange a secret key over a public, untrusted quantum channel. Compared to classical key exchange, QKD achieves everlasting security: after the protocol execution the key is secure against adversaries that can do unbounded computations. On the flip side, while classical key exchange can be achieved non-interactively (with two simultaneous messages between Alice and Bob), no non-interactive protocol is known that provides everlasting secur…

ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking
Shyma Alhuwaider, Motasem Alfarra, Juan C. Perez, Merey Ramazanova, Bernard Ghanem
https://arxiv.org/abs/2509.02182

ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking
We introduce a novel tracklet-based dataset for benchmarking test-time adaptation (TTA) methods. The aim of this dataset is to mimic the intricate challenges encountered in real-world environments such as images captured by hand-held cameras, self-driving cars, etc. The current benchmarks for TTA focus on how models face distribution shifts, when deployed, and on violations to the customary independent-and-identically-distributed (i.i.d.) assumption in machine learning. Yet, these benchmarks fa…

From Noisy Labels to Intrinsic Structure: A Geometric-Structural Dual-Guided Framework for Noise-Robust Medical Image Segmentation
Tao Wang, Zhenxuan Zhang, Yuanbo Zhou, Xinlin Zhang, Yuanbin Chen, Tao Tan, Guang Yang, Tong Tong
https://arxiv.org/abs/2509.02419

From Noisy Labels to Intrinsic Structure: A Geometric-Structural Dual-Guided Framework for Noise-Robust Medical Image Segmentation
The effectiveness of convolutional neural networks in medical image segmentation relies on large-scale, high-quality annotations, which are costly and time-consuming to obtain. Even expert-labeled datasets inevitably contain noise arising from subjectivity and coarse delineations, which disrupt feature learning and adversely impact model performance. To address these challenges, this study propose a Geometric-Structural Dual-Guided Network (GSD-Net), which integrates geometric and structural cu…

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
Ruohao Guo, Afshin Oroojlooy, Roshan Sridhar, Miguel Ballesteros, Alan Ritter, Dan Roth
https://arxiv.org/abs/2510.02286

Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction settings, where attackers strategically adapt their prompts across conversation turns and pose a more critical yet realistic challenge. Existing approaches that discover safety vulnerabilities either rely on manual red-teaming with human experts or employ automated methods using pre-defined templates and human-curated attack data, with most focusing on sin…

Towards Adversarial Training under Hyperspectral Images
Weihua Zhang, Chengze Jiang, Jie Gui, Lu Dong
https://arxiv.org/abs/2510.01014 https://arxiv.org/pd…

Towards Adversarial Training under Hyperspectral Images
Recent studies have revealed that hyperspectral classification models based on deep learning are highly vulnerable to adversarial attacks, which pose significant security risks. Although several approaches have attempted to enhance adversarial robustness by modifying network architectures, these methods often rely on customized designs that limit scalability and fail to defend effectively against strong attacks. To address these challenges, we introduce adversarial training to the hyperspectral…