AIBearisharXiv – CS AI · Jun 17/10
🧠Researchers demonstrate a novel poisoning attack on retrieval-augmented text-to-music systems where attackers inject malicious captions into music databases to manipulate generation outputs toward attacker-chosen targets while maintaining alignment with original user prompts. The attack reveals a critical integrity vulnerability in AI systems that depend on external knowledge bases for prompt augmentation.
AIBearisharXiv – CS AI · May 127/10
🧠Researchers have discovered ShadowMerge, a novel poisoning attack that exploits vulnerabilities in graph-based agent memory systems used by LLM agents. The attack achieves a 93.8% success rate by injecting malicious relations that conflict with benign data, enabling attackers to manipulate agent behavior while evading existing security defenses.
AIBearisharXiv – CS AI · May 127/10
🧠Researchers demonstrate 'Oracle Poisoning,' a novel attack where adversaries corrupt knowledge graphs used by AI agents, causing them to reach incorrect conclusions through valid reasoning. Testing across nine models from three providers shows all models accept fabricated data at 100% under moderate attack sophistication, revealing a critical vulnerability in production-scale agentic systems that differs fundamentally from prompt injection attacks.
🧠 GPT-5
CryptoBearishCoinDesk · Apr 307/10
⛓️A weather-related bet on Polymarket has exposed critical vulnerabilities in how prediction markets settle trades based on real-world data. The incident reveals that as more tangible outcomes become tradable on blockchain platforms, data integrity and certification—not the trading mechanism itself—emerges as the true systemic constraint for market reliability.
AINeutralarXiv – CS AI · Apr 157/10
🧠A new framework addresses dataset safety for autonomous driving AI systems by aligning with ISO/PAS 8800 guidelines. The paper establishes structured processes for data collection, annotation, curation, and maintenance while proposing verification strategies to mitigate risks from dataset insufficiencies in perception systems.
AI × CryptoBullishCoinDesk · Apr 147/10
🤖SkyMapper has launched a dedicated Avalanche-based blockchain network to record and secure telescope observations from observatories worldwide, creating immutable digital records of astronomical data. This integration demonstrates how blockchain technology can enhance data integrity and accessibility in scientific research, bridging DeFi infrastructure with academic applications.
$AVAX
AINeutralarXiv – CS AI · 6d ago5/10
🧠Researchers have developed Miffie, an AI-powered framework that automates database normalization using large language models with a dual-model self-refinement architecture. The system combines schema generation and verification modules to eliminate data anomalies while maintaining high accuracy, reducing manual effort by data engineers.
CryptoNeutralBlockonomi · Apr 176/10
⛓️TRM Labs has developed an advanced system to detect and reconcile blockchain reorganizations (reorgs) across EVM networks, addressing the challenge that reorgs alter transaction positions, timestamps, and execution outcomes. The solution uses layered detection and reconciliation mechanisms to handle real-time data processing without waiting for finality, improving data integrity for compliance and analytics platforms.
AINeutralarXiv – CS AI · Apr 156/10
🧠Researchers introduce wSSAS, a deterministic framework that enhances Large Language Model text categorization by combining hierarchical classification with signal-to-noise filtering to improve accuracy and reproducibility. Testing across Google Business, Amazon Product, and Goodreads reviews demonstrates significant improvements in clustering integrity and reduced categorization entropy.
🧠 Gemini
AIBearishMIT News – AI · Feb 96/107
🧠A new study reveals that online platforms ranking large language models (LLMs) can produce unreliable results, with rankings significantly changing when just a small portion of crowdsourced data is removed. This highlights potential vulnerabilities in how AI model performance is evaluated and compared publicly.
