Stride
PulseAugur coverage of Stride — every cluster mentioning Stride across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
LLMs enhance smart grid cyber-physical attack path identification
A new research paper proposes a framework that uses large language models (LLMs) to identify potential cyber-physical attack paths in smart grids. This LLM-guided approach integrates system topology with threat modeling…
-
New STRIDE benchmark reveals spatiotemporal reasoning gaps in driving AI
Researchers have introduced STRIDE, a new benchmark designed to evaluate the spatiotemporal reasoning capabilities of vision-language models (VLMs) in complex and safety-critical autonomous driving scenarios. The benchm…
-
Stride framework advances infographic generation with scale-aware multi-agent refinement
Researchers have introduced Stride, a novel multi-agent framework designed to enhance infographic generation. Stride addresses the challenge of scale mismatch in iterative refinement by separating constraint evaluation …
-
New STRIDE model improves video continuation with semantic foresight
Researchers have introduced STRIDE (STructural RegIsters for Decoupled Extrapolation), a novel large vision model architecture designed to improve the coherence of auto-regressive video continuation, particularly for dr…
-
New STRIDE framework enhances glioblastoma MRI analysis for disease evolution
Researchers have developed STRIDE, a novel framework designed to improve the assessment of disease evolution in longitudinal glioblastoma MRI scans. This method combines a lesion-prior-guided spatial representation usin…
-
New research advances on-policy distillation for LLM training · 6 sources tracked
Researchers are developing advanced techniques for on-policy distillation (OPD), a method used to improve large language models. New approaches like $\gamma$OPD and STRIDE aim to enhance optimization stability and effic…
-
Generative AI tool AegisShield democratizes cyber threat modeling
Researchers have developed AegisShield, a generative AI tool designed to automate and simplify cyber threat modeling, particularly for organizations with limited resources. The tool integrates the STRIDE framework and M…
-
Garry Tan's gstack enhances Claude Code for engineering workflows
The gstack configuration for Claude Code, developed by Garry Tan, is a highly-regarded tool for managing engineering workflows, boasting over 122,000 GitHub stars. It effectively simulates a virtual engineering team wit…
-
New research categorizes risks in AI-powered fact-checking systems
A new paper published on arXiv outlines a taxonomy of risks associated with automated fact-checking systems, particularly those employing AI and large language models. The research identifies 32 specific risks, categori…
-
Hivebook launches public agent knowledge cache to solve AI bugs
A new platform called Hivebook has been developed to create a public, agent-readable cache of knowledge, addressing the issue of AI agents repeatedly encountering and forgetting solutions to common problems like CORS er…
-
New STRIDE framework enhances LLM reasoning with verifiable rewards
Researchers have introduced STRIDE, a novel framework for Reinforcement Learning with Verifiable Rewards (RLVR) designed to enhance the reasoning capabilities of large language models. Unlike previous methods that rely …
-
STRIDE-GPT tool models AI app threats, logs context, limits tokens
STRIDE-GPT is an open-source tool designed to generate STRIDE threat models for AI applications by analyzing architecture descriptions. It emphasizes treating LLM-specific assets like system prompts, RAG documents, and …
-
LLM attack benchmarks show significant gaps in security coverage
Researchers have developed a new framework to audit the coverage of LLM attack benchmarks, revealing significant gaps in current evaluations. Their analysis of six public benchmarks showed they collectively cover less t…
-
Domain-adapted LLMs show mixed results for 5G threat modeling
Researchers evaluated domain-adapted language models for threat modeling in 5G security using the STRIDE approach. Their empirical study, involving 52 configurations across 8 language models, found that domain adaptatio…
-
LLM-enabled robots face holistic threat modeling from cyber to physical actuation
Researchers have developed a new threat modeling framework for robotic systems that integrate large language models (LLMs). This framework analyzes how conventional cyber threats, adversarial attacks, and conversational…