y0news
AnalyticsDigestsSourcesTopicsRSSAICrypto

#cryptographic-hardness News & Analysis

1 article tagged with #cryptographic-hardness. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

1 articles
AIBearisharXiv – CS AI · 5h ago7/10
🧠

Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions

Researchers present Sparse Backdoor, a supply-chain attack that embeds undetectable backdoors into pre-trained image classifiers by injecting sparse perturbations masked with Gaussian noise. The attack is proven computationally infeasible to distinguish from original models under standard hardness assumptions, raising critical security concerns for AI model deployment and verification.