y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#ai-defense News & Analysis

31 articles tagged with #ai-defense. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

31 articles
AINeutralarXiv – CS AI · Apr 146/10
🧠

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind

Researchers introduce ToM-SB, a novel challenge where AI defenders must use theory-of-mind reasoning to deceive attackers trying to extract sensitive information. Through reinforcement learning, trained models outperform frontier LLMs like GPT-4 and Gemini-Pro, revealing an emergent bidirectional relationship between belief modeling and deception capabilities.

🧠 GPT-5
AIBullisharXiv – CS AI · Mar 37/108
🧠

DualSentinel: A Lightweight Framework for Detecting Targeted Attacks in Black-box LLM via Dual Entropy Lull Pattern

Researchers introduce DualSentinel, a lightweight framework for detecting targeted attacks on Large Language Models by identifying 'Entropy Lull' patterns - periods of abnormally low token probability entropy that indicate when LLMs are being coercively controlled. The system uses dual-check verification to accurately detect backdoor and prompt injection attacks with near-zero false positives while maintaining minimal computational overhead.

$NEAR
AIBearishOpenAI News · Feb 256/106
🧠

Disrupting malicious uses of AI | February 2026

A new threat report analyzes how malicious actors are combining AI models with websites and social platforms to carry out attacks. The report examines the implications of these AI-powered threats for detection and defense systems.

AIBullishOpenAI News · Oct 286/104
🧠

Doppel’s AI defense system stops attacks before they spread

Doppel has developed an AI defense system using OpenAI's GPT-5 and reinforcement fine-tuning to prevent deepfake and impersonation attacks before they spread. The system reduces analyst workloads by 80% and cuts threat response times from hours to minutes.

AINeutralOpenAI News · Aug 226/106
🧠

Testing robustness against unforeseen adversaries

Researchers have developed a new method to evaluate neural network classifiers' ability to defend against previously unseen adversarial attacks. The approach introduces the UAR (Unforeseen Attack Robustness) metric to assess model performance against unanticipated threats and emphasizes testing across diverse attack scenarios.

GeneralNeutralCrypto Briefing · Jun 245/10
📰

Trump administration unveils AI-designed nuclear test flight vehicle at Great American State Fair

The Trump administration has unveiled an AI-designed nuclear test flight vehicle, showcasing advances in AI-driven innovation within defense technology. While AI acceleration in nuclear systems may expedite development cycles, commercial applications remain severely limited due to classification constraints and national security restrictions.

Trump administration unveils AI-designed nuclear test flight vehicle at Great American State Fair
🏢 Meta
← PrevPage 2 of 2