LLM Security

New Research Exposes How LLMs Fall for Fake Evidence

Researchers reveal how large language models can be manipulated with fabricated evidence, raising critical questions about AI reliability and the spread of misinformation through synthetic content.

LLM Quantization

FLRQ: Faster LLM Quantization via Low-Rank Matrix Sketching

New quantization method FLRQ achieves up to 2.5x faster compression of large language models while maintaining accuracy through flexible low-rank matrix approximation techniques.

deepfakes

UK Government Demands X Platform Action on Grok Deepfakes

The UK government pressures Elon Musk's X platform to address AI-generated deepfakes created by Grok chatbot, marking escalating regulatory scrutiny of synthetic media on social platforms.

deepfake detection

UNITE Detection System Advances Multi-Modal Deepfake Analysis

New UNITE framework combines facial, audio, and temporal analysis for comprehensive deepfake detection, moving beyond single-modality approaches that struggle with advanced synthetic media.

deepfake fraud

Deepfake Fraud Tools Falling Short of Criminal Expectations

Despite fears of sophisticated AI-powered fraud, deepfake tools are proving less effective than criminals anticipated. New analysis reveals the gap between hype and reality in synthetic media attacks.

embeddings

How AI Embeddings Power Everything From Search to Deepfakes

Embeddings transform words, images, and audio into mathematical vectors that AI uses to understand meaning. This core technology powers everything from search engines to deepfake detection systems.

LLM

Proactive Memory Extraction Advances LLM Agent Capabilities

New research proposes proactive memory extraction for LLM agents, moving beyond static summarization to enable more dynamic knowledge retention and recall in autonomous AI systems.

LLM unlearning

Dual-Granularity Data Synthesis Advances LLM Unlearning Methods

New research introduces domain-to-instance framework for generating synthetic data to help large language models selectively forget harmful knowledge while preserving useful capabilities.

AI research

How Test Set Contamination Skews Generative AI Evaluations

New research quantifies how training data contamination affects generative model benchmarks, revealing critical implications for evaluating deepfake detectors and synthetic media generators.

AI safety

GuardEval: New Benchmark Tests LLM Content Moderators

Researchers introduce GuardEval, a comprehensive benchmark evaluating LLM moderators across safety, fairness, and robustness dimensions—critical metrics for AI content authentication systems.

LLM Research

Agent Drift: Measuring LLM Behavior Decay in Multi-Agent Systems

New research quantifies how LLM agents degrade over extended interactions in multi-agent systems, revealing critical reliability challenges for production AI deployments.

Explainable AI

xDNN(ASP): Logic-Based Explainability for Neural Networks

New research combines deep neural networks with Answer Set Programming to generate human-readable explanations for AI decisions, advancing interpretability crucial for detection systems.