The paper systematically measures the risk of current image-to-3D models generating harmful geometries, finding that these models are effective at reconstruction and existing safeguards are insufficie…

The paper introduces the Black-Hole Attack, a poisoning vulnerability that exploits geometric defects in high-dimensional embedding spaces to force malicious vectors into the top-k results of vector d…

The paper introduces PsychoPass, a framework that analyzes the geometric trajectory of multi-turn conversations in embedding space to detect adversarial intent early, before harmful content is generat…

The paper demonstrates that high detection performance against obfuscated prompts does not guarantee representational robustness, identifying a phenomenon called latent embedding collapse.

The paper introduces Tail-risk Intrinsic Geometric Smoothing (TIGS), a plug-and-play, inference-time defense that suppresses backdoor attacks on LLMs by structurally smoothing the attention mechanism…

The paper proposes GeoMark, a geometry-aware localized watermarking framework that robustly protects Embedding-as-a-Service (EaaS) against model stealing and copyright infringement while preserving ut…

The paper introduces MoCo-EA, an evolutionary attack method that replaces standard crossover with a continuous Bézier curve interpolation to efficiently exploit the connected manifold structure of adv…

The paper introduces PRISM, a novel representation learning framework that learns isometric embeddings by explicitly modeling the intrinsic geodesic metric of 3D surfaces, achieving superior performan…

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

The paper demonstrates that cryptographically undetectable backdoors can be embedded into modern, state-of-the-art neural networks by exploiting inherent, latent geometric properties of the learned re…

The paper proposes a unified, architecture-agnostic framework that significantly improves the robustness of deepfake image detectors against adversarial attacks by focusing on higher-order frequency s…

The paper investigates applying Riemannian optimization techniques to low-rank matrix parameters for deep learning, but finds that the proposed methods do not conclusively outperform the AdamW baselin…

The paper systematically evaluates static and dynamic adversarial attacks on the ALEX learned index, finding that while static poisoning has minimal impact, dynamic attacks can cause significant slowd…

GJDNet proposes a joint disentanglement framework to enhance the robustness of Graph Neural Networks against adversarial attacks by simultaneously stabilizing node representations and decision boundar…

MARGIN proposes a margin-aware framework to detect software vulnerabilities by addressing geometric distortions caused by frequency and difficulty imbalances in embedding space, achieving superior per…

The paper introduces 'adversarial restlessness,' an activation-level signature in LLM residual streams, to detect multi-turn prompt injection attacks with high accuracy.

The paper evaluates the adversarial robustness of two open-source Vision-Language Models (LLaVA and Qwen2.5-VL) in a simulated e-commerce environment, finding that while LLaVA is vulnerable to gradien…

The paper demonstrates that fine-tuning safety guard models on benign data can catastrophically collapse their safety alignment, proposing Fisher-Weighted Safety Subspace Regularization (FW-SSR) to ac…

The paper introduces a robust, two-part framework (HyPE and HyPS) using hyperbolic geometry to efficiently detect and sanitize malicious prompts targeting Vision-Language Models (VLMs).