LLM Security
New research reveals how adversarial control tokens can manipulate LLM-as-a-Judge systems into completely reversing their binary decisions, exposing critical vulnerabilities in AI evaluation pipelines.
AI Safety
New research explores how Bayesian uncertainty quantification in neural QA systems can improve AI reliability by enabling models to recognize and communicate their own limitations.
Deepfake Detection
Gartner positions Reality Defender as a leading deepfake detection solution as enterprises face mounting synthetic media fraud risks across video, audio, and image authentication.
LLM Architecture
Key-Value caching dramatically accelerates LLM inference by storing computed attention states. Understanding this technique is essential for building efficient AI video and synthetic media applications.
Deepfake Detection
Google launches new detection technology to identify AI-altered videos as deepfake concerns grow. The tool aims to help users verify video authenticity amid rising synthetic media threats.
Deepfake Detection
LexisNexis launches enhanced IDVerse platform combining AI-powered document authentication with advanced deepfake detection to combat synthetic identity fraud in financial services verification.
Nvidia
The Biden administration initiates a new review of Nvidia's advanced AI chip exports to China, potentially tightening restrictions on technology critical for training generative AI models.
mechanistic interpretability
Researchers introduce SALVE, combining sparse autoencoders with latent vector editing for precise mechanistic control over neural network behaviors and outputs.
AMD
AMD researchers unveil AIE4ML, an end-to-end compiler framework that maps neural networks to next-gen AI Engines, achieving significant speedups over CPU implementations for ML workloads.
LLM
Researchers propose efficient Shapley value approximation using language model arithmetic to determine which training data samples matter most for LLM fine-tuning.
multi-modal AI
New research introduces MMGR, a framework that enables AI models to perform generative reasoning across multiple modalities including text, images, and video.
Deepfake Detection
MITRE has identified deepfake face-swap tools as a growing threat to Know Your Customer identity verification systems, highlighting vulnerabilities in financial authentication.