AI security
Open Framework Detects Attack Patterns in Multi-Agent AI Systems
New research introduces an open framework for training security models that detect temporal attack patterns in multi-agent AI workflows through trace-based analysis.
Research
neural-networks
Sphere Neural Networks: Guaranteed Decision Regions for AI
New neural architecture creates mathematically guaranteed decision regions using hyperspheres, enabling AI systems to know when they're uncertain rather than making unreliable predictions.
AI Detection
Unknown-Aware Attribution: Identifying AI Content Origins
New research tackles the challenge of attributing AI-generated content to specific models while handling unknown generators—critical for deepfake detection and digital authenticity verification.
LLM Security
Vocabulary Trojans: A New Threat to LLM Security and Trust
Researchers reveal how malicious actors can embed hidden backdoors in LLMs through vocabulary manipulation, enabling stealthy sabotage that evades detection methods.
LLM
HaluNet: Multi-Granular Uncertainty for LLM Hallucination Detecti
New research introduces HaluNet, a framework using multi-granular uncertainty modeling to efficiently detect hallucinations in LLM question answering systems.
AI Safety
Neuroscience-Inspired AI: Actions, Memory and Safety Design
New research proposes integrating actions, compositional structure, and episodic memory from neuroscience to build safer, more interpretable AI systems that could transform how we approach AI trustworthiness.
AI Safety
DarkPatterns-LLM: New Benchmark Detects Manipulative AI Behavior
Researchers introduce DarkPatterns-LLM, a multi-layer benchmark designed to identify and evaluate manipulative behaviors in large language models, advancing AI safety and authenticity research.
AI Detection
New Study Shows Humans Struggle to Identify AI-Generated Images
Research reveals significant limitations in human ability to detect AI-generated images, raising critical questions about synthetic media verification and the future of visual authenticity.
synthetic data
RL-Driven Synthetic Data Generation: A New Training Paradigm
New research explores how reinforcement learning can optimize synthetic data generation, with implications for training more capable AI video and media generation models.
AI agents
Blockchain-Monitored AI Agents: A New Trust Architecture
New research proposes combining blockchain monitoring with agentic AI to create verifiable perception-reasoning-action pipelines, addressing critical trust and authenticity challenges in autonomous AI systems.
Generative AI
New Taylor-Based Matrix Exponential Method Boosts Generative AI F
Researchers propose a Taylor-based approach that outperforms the classic Paterson-Stockmeyer method for computing matrix exponentials in flow-based generative AI models, offering efficiency gains for video and image synthesis.
AI Safety
Formal Verification Breakthrough for Early-Exit Neural Networks
New research bridges efficiency and safety by developing formal verification methods for neural networks with early exits, enabling mathematically proven safety guarantees for adaptive AI systems.