y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#inference-defense News & Analysis

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

2 articles
AIBullisharXiv – CS AI · Jun 117/10
🧠

ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit Mixing

Researchers introduce ALIGNBEAM, a training-free inference-time defense that transfers safety alignment between different language model families by translating logits across vocabularies. The method addresses a critical gap where existing safety defenses fail for cross-family model pairs, enabling safety constraints without modifying model weights or retraining.

AIBullisharXiv – CS AI · May 127/10
🧠

Mitigating Many-shot Jailbreak Attacks with One Single Demonstration

Researchers demonstrate that many-shot jailbreak attacks on language models work by inducing progressive activation drift through implicit fine-tuning, and propose a simple defense using a single safety demonstration at inference time that counteracts this drift without requiring parameter modifications or white-box access.