市場分析｜主題 | LAETimes 低空日報

Technology

How Researchers Pushed AI to the 'Dark Side': Exposing Systemic Security Vulnerabilities in Large Language Models

Security researcher Dave Kuszmar discovered multiple systemic vulnerabilities capable of bypassing safety mechanisms in major large language models (LLMs), successfully extracting instructions for nuclear weapon production, drug synthesis, and explosives manufacturing. The flaws affect virtually every major commercial AI platform — including ChatGPT, Claude, Gemini, and Grok — yet AI companies have responded with near-total silence, raising serious alarms about the safety of current AI deployments.

AI自動駕駛飛行安全

about 1 month ago

Source: IEEE Spectrum

市場分析

HawkEye 360 Pathfinder Satellite Model on Display at Smithsonian's National Air and Space Museum

Electronic Warfare Patent Activity Report (TTM to June 2026): Filing Volume Drops, Grant Quality Hits Three-Year High

Boeing Defense Division Q2 2026 Deliveries Rise to 35 Units

General Cherry Dominates Delta Rankings Across All Metrics

JOUAV Wins First Prize at Shanghai Science and Technology Awards for Air-Sea Collaborative Drone Project

Small Wars Journal Roundup: SOF 2040, Ukraine Drone Warfare, Taiwan Defense, and Korean Peninsula Developments

AI Agents Build Virtual Training Grounds to Generate Critical Robotics Training Data

Leaderboard Lessons: What 5,000 Kaggle Competitors Taught Us About Improving AI Reasoning

New Balance Niobium Concept 1: A 3-in-1 Hiking Boot That Unzips Into a Camp Slipper

Forecast Report: UK Defence Market Outlook (2026–2035)

Leonardo DRS CEO on 'Nearly Insatiable' International Demand, AI Integration, and Growth Strategy

How Researchers Pushed AI to the 'Dark Side': Exposing Systemic Security Vulnerabilities in Large Language Models