NewsHive
CONTACT USANALYST PORTAL →
aiBACKGROUND

AlignPoison: Conditional Targeted Poisoning of Generative Recommenders via Decod

BACKGROUND
1 SIGNALFIRST DETECTED 14 October 2026
Narrative synthesis pending — 1 signal collected.
How the story developed
14 Oct
4.1
Other feeds and industry voices
20 Mar
Semantic Chameleon: Corpus-Dependent Poisoning Attacks and Defenses in RAG Systems

arXiv:2603.18034v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems extend large language models (LLMs) with external knowledge sources but introduce

REPORT · WHAT · ArXiv CS.AIOPEN STORY
25 Mar
ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

arXiv:2603.22934v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) improves the reliability of large language model applications by grounding generation in

REPORT · WHAT · ArXiv CS.AIOPEN STORY
26 Mar
Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation

arXiv:2603.22335v1 Announce Type: cross Abstract: Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical

REPORT · WHAT · ArXiv CS.AIOPEN STORY
28 Sept
Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems

arXiv:2609.30383v1 Announce Type: new Abstract: A skill is a modular package of natural-language instructions, executable scripts, and reference resources that an agent can load

REPORT · WHAT · ArXiv CS.AIOPEN STORY
Sources
ArXiv CS.AI

NewsHive monitors these sources continuously. All signal titles above link to the original reporting.

Intelligence by NewsHive. Need help navigating what this means for your business? Contact GeekyBee →