AI Research
New research introduces Jr. AI Scientist, an autonomous system that conducts scientific exploration from baseline papers. The study includes comprehensive risk assessment frameworks for AI-driven research automation.
LLM Security
Researchers introduce AdversariaLLM, a modular framework for evaluating large language model vulnerabilities. The open-source toolbox standardizes adversarial testing methodologies for AI security research.
LLM
New research introduces KnowThyself, an agentic assistant that helps researchers understand how large language models work internally through automated interpretability analysis and mechanistic understanding.
deepfake-detection
Researchers propose a gated temporal attention-based intra prediction framework for robust deepfake video detection, leveraging temporal inconsistencies in manipulated footage to improve detection accuracy across multiple datasets.
Deepfakes
A deepfake video falsely depicting journalist Navika Kumar cleaning politician Amit Shah's shoes has spread widely across social media, highlighting ongoing challenges with AI-generated misinformation targeting public figures in India.
AI Security
New research demonstrates how multiple LLMs working together can generate adaptive adversarial attacks that bypass AI safety filters. The technique uses collaborative reasoning to craft prompts that exploit model vulnerabilities more effectively than single-agent approaches.
AI Safety
Researchers introduce comprehensive evaluation framework for control protocols designed to manage untrusted AI agents, addressing key safety challenges as autonomous systems become more capable and potentially misaligned.
AI Security
New research demonstrates how synthetic data generation can systematically optimize adversarial attacks against AI agents, revealing critical security vulnerabilities in autonomous systems through automated testing frameworks.
Generative AI
Researchers propose mathematical framework challenging conventional precision-recall metrics for generative models, offering better evaluation for AI video, image synthesis, and deepfake quality assessment.
LLM Agents
Researchers introduce Deep Ideation, a framework that guides LLM agents through scientific concept networks to generate novel research ideas, demonstrating how structured knowledge graphs can enhance AI creativity in scientific discovery.
Deepfakes
AI-manipulated video falsely depicts Bollywood actor Sonu Sood endorsing Bihar politician Khesari Yadav, highlighting synthetic media's growing role in Indian electoral politics as deepfakes target regional elections.
Synthetic Data
Large language models are revolutionizing how AI systems are trained by generating synthetic datasets that overcome data scarcity challenges. This technical approach is transforming model development across domains including synthetic media generation.