y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#open-weight-llms News & Analysis

2 articles tagged with #open-weight-llms. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

2 articles
AIBearisharXiv – CS AI · May 287/10
🧠

Position: Retire the "Positive Backdoor" Label -- Secret Alignment Requires Strict and Systematic Evaluation

A research position paper argues the AI/ML community should abandon the "positive backdoor" terminology and instead rigorously evaluate trigger-activated hidden behaviors as "Secret Alignment." Researchers found that existing implementations show significant brittleness in security properties, particularly in confidentiality, integrity, and availability—revealing that protective claims lack standardized evaluation frameworks.

AIBearisharXiv – CS AI · Mar 127/10
🧠

Amnesia: Adversarial Semantic Layer Specific Activation Steering in Large Language Models

Researchers have developed 'Amnesia,' a lightweight adversarial attack that bypasses safety mechanisms in open-weight Large Language Models by manipulating internal transformer states. The attack enables generation of harmful content without requiring fine-tuning or additional training, highlighting vulnerabilities in current LLM safety measures.