y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#model-defense News & Analysis

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

2 articles
AINeutralarXiv – CS AI · May 77/10
🧠

SoK: Robustness in Large Language Models against Jailbreak Attacks

Researchers introduce Security Cube, a comprehensive evaluation framework for assessing Large Language Model robustness against jailbreak attacks. The study systematically catalogs existing attack and defense methods while establishing benchmarks across 13 attack vectors and 5 defense mechanisms, revealing critical gaps in current LLM safety practices.

AINeutralarXiv – CS AI · Jun 116/10
🧠

Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization

Researchers demonstrate that reinforcement learning (RL) can disrupt gradient-based adversarial attacks on deep neural networks by creating unstable gradient structures, and when combined with adversarial training, provides dual-layer defense that significantly outperforms traditional supervised learning approaches across multiple attack types.